Satellite remote first-aid medical rescue method and system for offshore ocean vessels

Abstract

The invention discloses a satellite remote first-aid medical rescue method and system for offshore ocean vessels, and the method comprises the steps: obtaining real-time physical sign data and image information from medical equipment through a satellite communication link, carrying out the format verification of the physical sign data and image information through a preset access protocol, and judging the integrity of the physical sign data and the image information. And according to the integrity judgment result, carrying out separation processing on the sign data and the image information, and carrying out priority ranking on the sign data by adopting a classification rule to obtain a preliminary classification result. And for high-priority sign data in the preliminary classification result, performing anomaly detection by adopting an algorithm, and marking high-risk data to form an anomaly mark set. And according to the abnormal mark set, performing association matching on the high-risk data and corresponding image information to generate a joint data set. Therefore, the response speed and decision-making precision of offshore remote first-aid medical rescue are improved.

Description

Technical Field

[0001] This invention relates to the field of remote emergency rescue technology, and in particular to a satellite remote emergency medical rescue method and system for ocean-going vessels. Background Technology

[0002] As a core component of the emergency management system, maritime rescue plays a crucial role in ensuring the safety of crew members and maintaining maritime transport order during ocean voyages.

[0003] Ocean-going vessels are far from land, and the handling of sudden illnesses or accidental injuries relies heavily on remote medical support. However, existing technologies face multiple technical bottlenecks in the complex marine environment. Satellite communication links, as the main data transmission channel, are highly susceptible to severe weather, signal attenuation in high-latitude regions, and equipment mobility, resulting in frequent interruptions or distortions of real-time vital sign data and image information obtained from shipboard medical equipment.

[0004] During data transmission, the lack of format verification mechanisms makes it difficult to guarantee the integrity of vital sign data and image information. The receiving end often fails to effectively parse key information due to missing data packets or protocol incompatibility. The current situation of mixed transmission of vital sign data and image information results in low processing efficiency, and the lack of a targeted separation mechanism leads to a chaotic subsequent analysis process.

[0005] In the data prioritization stage, the existing system fails to dynamically sort vital sign data according to the degree of medical urgency. High-risk indicators, such as abnormal heart rate or sudden drops in blood pressure, cannot be identified in a timely manner, delaying risk warnings. Insufficient anomaly detection capabilities further exacerbate the problem; the system lacks real-time pattern matching of vital sign data features, making it difficult to automatically mark potentially high-risk data points, hindering doctors from quickly identifying critical situations. There is a disconnect between imaging information and vital sign data, preventing the formation of a unified view of patient health and affecting the accuracy of remote diagnosis. The diversity of data formats makes standardization difficult, and the poor interoperability between vital sign data and imaging information generated by different devices hinders efficient information integration.

[0006] With limited transmission resources, the strategy of transmitting all data equally prevents high-risk data from obtaining priority channels, and critical medical information is often delayed or lost due to bandwidth contention. For example, when a ship encounters a storm, electrocardiogram and imaging data collected by medical equipment are transmitted in fragments due to unstable communication. Onshore medical institutions can only obtain scattered information and cannot build a complete patient profile, ultimately leading to delays in treatment planning. These technical deficiencies collectively restrict the response speed and decision-making accuracy of maritime remote emergency rescue. At a deeper level, the lack of a unified, integrated platform that connects the command center, medical institutions, and on-site vessels further leads to fragmentation at the operational level due to the aforementioned data-level problems. For example, rescue orders cannot be accurately issued, on-site treatment is disconnected from rear consultation, and medical resources cannot be efficiently dispatched across departments. There is an urgent need to build a comprehensive technical framework that can ensure data integrity, intelligent priority scheduling, and priority transmission of high-risk information, while serving integrated emergency rescue operational collaboration. Summary of the Invention

[0007] This invention provides a satellite-based remote emergency medical rescue method and system for ocean-going vessels, which improves the response speed and decision-making accuracy of remote emergency medical rescue at sea. By ensuring data integrity, realizing intelligent priority scheduling, and prioritizing the transmission of high-risk information, it can effectively address communication challenges in complex marine environments.

[0008] To achieve the above objectives, in a first aspect, the present invention provides a satellite-based remote emergency medical rescue method for ocean-going vessels, comprising: acquiring real-time vital sign data and image information from medical equipment via a satellite communication link; performing format verification on the vital sign data and image information using a preset access protocol to determine the integrity of the vital sign data and image information; separating the vital sign data and image information based on the integrity determination result; prioritizing the vital sign data using classification rules to obtain a preliminary classification result; performing anomaly detection using an algorithm on the high-priority vital sign data in the preliminary classification result, marking high-risk data to form an anomaly marker set; associating and matching the high-risk data with corresponding image information based on the anomaly marker set to generate a joint data group; unifying the format of the vital sign data and image information using standardization conversion rules for the joint data group to obtain a standardized data stream; generating a priority transmission queue for the high-risk data portion of the standardized data stream, forwarding it via the satellite communication link, and recording the transmission status; storing the transmission log in a preset database for successfully forwarded standardized data streams and obtaining storage confirmation information.

[0009] Secondly, this invention provides a satellite-based remote emergency medical rescue system for ocean-going vessels, based on the satellite-based remote emergency medical rescue method for ocean-going vessels as described in the first aspect above. The system includes: an integrity judgment module, a classification result acquisition module, an anomaly marker set formation module, a joint data group generation module, a standardized data stream acquisition module, a transmission status recording module, and a confirmation information acquisition module. The integrity judgment module acquires real-time vital sign data and image information from medical devices via a satellite communication link, performs format verification on the vital sign data and image information using a preset access protocol, and determines the integrity of the vital sign data and image information. The classification result acquisition module separates the vital sign data and image information according to the integrity judgment result, prioritizes the vital sign data using classification rules, and obtains a preliminary classification result. The anomaly marker set formation module performs anomaly detection using an algorithm on high-priority vital sign data in the preliminary classification result, marks high-risk data, and forms an anomaly marker set. The joint data group generation module associates and matches the high-risk data with corresponding image information based on the anomaly marker set to generate a joint data group. The standardized data stream acquisition module is used to unify the format of the vital sign data and image information using standardized conversion rules for the joint data set, thereby obtaining a standardized data stream. The transmission status recording module is used to generate a priority transmission queue for the high-risk data portion of the standardized data stream, forward it through the satellite communication link, and record the transmission status. The confirmation information acquisition module is used to store transmission logs in a preset database for successfully forwarded standardized data streams and obtain storage confirmation information.

[0010] Thirdly, the present invention provides an electronic device, comprising:

[0011] At least one processor; and

[0012] A memory that is communicatively connected to the at least one processor;

[0013] The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform the satellite-based remote emergency medical rescue method for ocean-going vessels as described above.

[0014] As can be seen from the above, the present invention provides a satellite-based remote emergency medical rescue method and system for ocean-going vessels. By acquiring real-time vital signs data and image information, performing format verification and integrity judgment, separating and processing the data and prioritizing it, detecting and marking high-risk anomalies, generating joint data groups through correlation matching, unifying the format to obtain a standardized data stream, generating a priority transmission queue for forwarding, and storing transmission logs, the present invention solves the problems in the background technology, improves the response speed and decision-making accuracy of remote emergency medical rescue at sea, and effectively addresses the communication challenges in complex marine environments by ensuring data integrity, realizing intelligent priority scheduling, and prioritizing the transmission of high-risk information. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a satellite-based remote emergency medical rescue method for ocean-going vessels, as described in Embodiment 1 of the present invention.

[0016] Figure 2 This is a schematic diagram of the structure of a satellite remote emergency medical rescue system for ocean-going vessels, as shown in Embodiment 2 of the present invention.

[0017] Figure 3 This is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] To facilitate understanding, the main implementation concepts of the various embodiments of the present invention will be briefly described first.

[0021] During medical rescue operations on ocean-going vessels, when crew members experience sudden illness, on-site personnel use terminals deployed with maritime emergency medical treatment systems (such as portable integrated rescue devices) or communication control boxes connected to medical equipment to access the integrated maritime emergency management platform via high-throughput satellite terminals. Due to the highly dynamic and uncertain marine environment, the communication link between medical rescue equipment and the command center and medical institutions via this platform exhibits significant instability. This instability leads to unreliable transmission and real-time sharing of critical vital signs data and image information, resulting in interruptions in the emergency response process and a lack of information for treatment decisions. Specifically, fluctuations in the communication link cause frequent interruptions in data transmission, making it difficult to guarantee the integrity of vital signs data and image information, affecting the timeliness and accuracy of the rescue system's decisions, and ultimately hindering the improvement of overall rescue efficiency.

[0022] For example, during ocean voyages, when ships are in remote waters far from the coast and encounter strong winds and waves, onboard medical equipment needs to transmit real-time vital signs data such as heart rate and blood pressure, as well as on-site image information, to the shore command center via satellite communication links. However, due to electromagnetic interference and signal attenuation in the maritime environment, communication links experience intermittent interruptions, resulting in the loss of vital sign data packets or incomplete transmission of image information. The command center can only receive fragmented data, unable to form a continuous patient status monitoring sequence. Medical experts cannot make accurate assessments and provide remote guidance based on real-time information, forcing delays in the implementation of emergency treatment measures and directly affecting the accuracy of on-site medical care.

[0023] If the aforementioned communication instability issues are not resolved, the reliability of data transmission in the maritime rescue system will be insufficient to meet emergency medical needs. The lack of critical vital sign information may lead to medical decisions based on incomplete or outdated data, increasing the risk to patients' lives. Furthermore, the management and coordination capabilities of rescue equipment will be continuously constrained, and the information linkage mechanism between the command center and medical institutions will fail, significantly reducing the coherence of the rescue process and the overall effectiveness of the system, ultimately adversely affecting the success rate of maritime life rescues.

[0024] Example 1, Figure 1 This is a flowchart illustrating a satellite-based remote emergency medical rescue method for ocean-going vessels, as described in Embodiment 1 of the present invention. Figure 1 As shown, Embodiment 1 provides a satellite-based remote emergency medical rescue method for ocean-going vessels, including:

[0025] The A100 acquires real-time vital sign data and image information from medical devices via a satellite communication link, and performs format verification on the vital sign data and image information using a preset access protocol to determine the integrity of the vital sign data and image information.

[0026] Specifically, medical devices (such as portable emergency medical devices that can be connected to maritime emergency medical systems) can be equipped with various sensors, such as electrocardiogram (ECG) sensors, blood pressure sensors, and blood oxygen sensors, to collect real-time vital signs data of patients. They can also be equipped with high-resolution cameras or ultrasound probes to acquire image information. After data acquisition, the data is transmitted to the shipborne data processing unit (built into or located outside the portable emergency medical device) via wired or wireless connections. Upon receiving the data, the shipborne data processing unit can perform preliminary format verification using simple header checks or packet length checks. Integrity checks can be performed based on packet counting, checksums, or simple file size comparisons to determine if data has been lost or corrupted during transmission. For example, suppose the shipborne medical device collects a patient's heart rate, blood pressure data, and an ultrasound image. This data is packaged and sent to the data processing unit via the shipborne local area network. Upon receiving the data, the data processing unit checks whether the header information of each packet conforms to preset specifications and calculates a checksum to verify the integrity of the data content.

[0027] A200, based on the integrity judgment result, separate the vital signs data and image information, and use classification rules to prioritize the vital signs data to obtain a preliminary classification result.

[0028] Specifically, if the integrity assessment result indicates that the data is complete, the data processing unit can store the vital signs data and imaging information into different memory areas or temporary files according to the data type identifier. For vital signs data, a set of classification rules based on medical expert experience or clinical guidelines can be preset. For example, vital signs data such as heart rate and blood pressure can be classified as "core vital signs," while body temperature and blood oxygen can be classified as "auxiliary vital signs." Priority ranking can be simply based on these classifications; for example, core vital signs data are given the highest priority, followed by auxiliary vital signs data. This forms a preliminary classification result containing the original data and its corresponding priority label. For example, continuing the above example, if the heart rate, blood pressure data, and ultrasound images are all complete, the system will identify the heart rate and blood pressure data as vital signs data and the ultrasound images as imaging information, and store them separately. Subsequently, the heart rate and blood pressure data are marked as "high priority," while other data such as body temperature are marked as "medium priority," forming a preliminary classification result.

[0029] A300 uses an algorithm to detect anomalies in the high-priority vital sign data in the preliminary classification results, marks high-risk data, and forms an anomaly label set.

[0030] Specifically, the data processing unit can filter data marked as high priority in the preliminary classification results. For these high-priority data, a simple threshold comparison-based algorithm can be used for anomaly detection. For example, if the preset normal range for heart rate is 60-100 beats per minute, and a heart rate consistently below 60 or above 100 is detected, it is marked as abnormal. Once an anomaly is detected, the system adds a "high-risk" label to the data and records the time of the anomaly, the data value, and the anomaly type. All these records with high-risk labels are collected to form an anomaly label set. For example, in the preliminary classification results, heart rate and blood pressure data are identified as high priority. The system analyzes the heart rate data and finds that the patient's heart rate consistently exceeds 120 beats per minute, exceeding the preset normal range. At this time, the heart rate data is marked as "high-risk" and recorded as "tachycardia," forming an anomaly label set along with other similar abnormal data.

[0031] A400: Based on the set of anomaly markers, the high-risk data is associated and matched with the corresponding image information to generate a joint data group.

[0032] Specifically, the data processing unit can traverse the set of anomaly markers. For each high-risk data point, based on its acquisition timestamp or patient ID, it searches for images in the previously stored, separately stored image information that are closest in time or related to the same patient. For example, if the high-risk data is a heart rate abnormality at a certain point in time, the system will attempt to find ultrasound images or live videos acquired before and after that time. Once a matching image is found, the high-risk vital sign data and the corresponding image information are logically linked together to form a joint data set. For example, the set of anomaly markers may contain high-risk data of a patient with tachycardia. Based on the acquisition time of this heart rate data, the system finds an image showing cardiac activity acquired within the same time period in the previously stored ultrasound images. These two pieces of information are correlated to form a joint data set, allowing doctors to view both heart rate values ​​and cardiac images simultaneously.

[0033] A500 uses standardized conversion rules to unify the format of the vital signs data and image information for the joint data set, resulting in a standardized data stream.

[0034] Specifically, the data processing unit can pre-define a common data format standard, such as a simplified version of HL7 or DICOM, or a custom JSON / XML format. For vital sign data in the combined dataset, its values ​​can be converted into a unified unit and representation. For image information, its resolution, encoding format, or compression method can be adjusted to conform to the standard. By applying these standardized conversion rules, data from different sources and in different formats are unified into a standardized data stream that is easy to process and transmit. For example, the combined dataset contains raw heart rate values ​​and a segment of ultrasound image in a specific encoding format. The system applies standardized conversion rules to convert the heart rate values ​​into a unified digital format and the ultrasound image into a common JPEG or MPEG format, thus obtaining a standardized data stream with a unified format.

[0035] A600, based on the standardized data stream, generates a priority transmission queue for the high-risk data portion, forwards it through the satellite communication link, and records the transmission status.

[0036] Specifically, the data processing unit identifies portions of the standardized data stream that originate from or are associated with high-risk data. These identified high-risk data portions are extracted and organized into a priority transmission queue according to their urgency or a pre-defined transmission strategy. Data in this queue is transmitted to the onshore medical center via a satellite communication link. During transmission, the system records the transmission time, reception confirmation, and any transmission error information for each data packet to track the transmission status. For example, the standardized data stream may contain standardized data on a patient's tachycardia and corresponding standardized ultrasound images. The system identifies this high-risk data and places it in the priority transmission queue. Subsequently, this data is transmitted via a shipborne satellite terminal through a satellite communication link to the onshore maritime emergency command platform, the maritime remote integrated medical treatment platform, or the receiving server at a hospital. The system records the transmission time of the data packets and awaits initial confirmation from the receiving server.

[0037] For the A700, for the successfully forwarded standardized data stream, the transmission log is stored in a preset database, and storage confirmation information is obtained.

[0038] Specifically, once the standardized data stream is successfully forwarded, the data processing unit generates a transmission log. This log may contain basic information such as transmission time, data type, sender, receiver, data size, transmission time, and transmission result. The transmission log is then sent to a pre-set database on board for storage. After successfully receiving and storing the log, the database returns a storage confirmation message to the data processing unit. For example, when a standardized data stream containing tachycardia data and ultrasound images is successfully sent to the onshore hospital's integrated maritime remote medical treatment platform, the system generates a transmission log recording "On [Date] at [Time], Patient A's high-risk data (tachycardia and ultrasound images) was successfully sent to the onshore hospital." This log is then sent to the onboard database for storage. After completing the storage, the database returns a "storage successful" confirmation message to the system.

[0039] Based on the above analysis, the technical concept of this invention, as the core data processing and communication guarantee mechanism of the integrated maritime emergency medical care IoT platform, demonstrates a significant technical contribution to solving the problem of remote emergency medical rescue for ocean-going vessels. This invention constructs an efficient and reliable satellite-based remote emergency medical rescue method for ocean-going vessels through the synergistic effects of data verification, classification, anomaly detection, correlation, standardization, priority transmission, and log storage. In the complex maritime environment, this method ensures the real-time and accurate transmission and sharing of critical medical data, significantly improving the efficiency and success rate of remote medical rescue, and exhibits clear progress and innovation compared to existing technologies.

[0040] In this embodiment, the step of generating a priority transmission queue for the high-risk data portion of the standardized data stream and forwarding it via the satellite communication link includes:

[0041] For the standardized data stream, the data fields are parsed to identify high-risk data identifiers.

[0042] The goal of parsing data fields and identifying high-risk data markers is to accurately locate and identify information crucial to patient safety from complex, standardized data streams. Specifically, a predefined data parser, based on medical data standards (such as HL7 or DICOM) or a custom data dictionary, can be used to perform structured analysis on various fields in the standardized data stream. For example, the system can be configured with a series of rules to mark key physiological parameters such as heart rate, blood pressure, and blood oxygen saturation as high-risk data when they exceed preset normal ranges (e.g., heart rate below 50 beats / min or above 120 beats / min). Alternatively, machine learning models, such as support vector machines (SVM) or neural networks, can be trained on historical medical data. This model can learn and identify data patterns that significantly deviate from normal physiological states, thereby automatically identifying and marking potentially high-risk data in real-time data streams. This method is particularly suitable for identifying complex anomalies involving multiple parameter correlations.

[0043] Based on the high-risk data identifier, the corresponding data content is extracted, and a priority transmission queue is constructed.

[0044] The purpose of extracting the corresponding data content and constructing a priority transmission queue is to separate identified high-risk data and its associated information from the standardized data stream and organize it into a priority transmission sequence to ensure that it can be processed and sent with priority. For example, the system can maintain a dynamic priority queue data structure. When a high-risk data identifier is detected, the data (including its original vital signs data, timestamp, and any associated image information) is immediately inserted into the highest priority position of the queue. In another implementation, multiple logical transmission channels or queues can be set up, such as an "emergency channel" and a "regular channel." Once data is marked as high-risk, the system routes it to the priority transmission queue corresponding to the "emergency channel" and allocates it higher bandwidth and scheduling priority to ensure that it can obtain priority transmission rights even when network resources are limited.

[0045] The data in the priority transmission queue is sent to the target receiving end in batches through the satellite communication link, and the transmission status feedback of each batch of data is obtained.

[0046] The system involves sending data from the priority transmission queue in batches to the target receiver and obtaining transmission status feedback for each batch. This aims to adapt to potential bandwidth limitations and instability in satellite communication links by dividing data into smaller batches for transmission, and to monitor the transmission process through a real-time feedback mechanism. For example, the system can employ an application-layer transmission mechanism based on the UDP protocol, dividing the data in the priority transmission queue into data packets of a predetermined size (e.g., each data packet contains 100KB of data) and assigning a unique sequence number to each packet. After sending each batch of data, the sender starts a timer and waits for an acknowledgment message from the target receiver, which may contain a list of successfully received data packet sequence numbers. Alternatively, an enhanced TCP protocol or a custom reliable UDP protocol can be used to implement the batch transmission and acknowledgment mechanism at the application layer. After sending a batch of data, the sender waits for a transmission status feedback report from the receiver, which details the received, lost, or corrupted data packets. This batch transmission strategy helps reduce the overall retransmission volume even when some data packets are lost due to fluctuations in link quality, by using smaller retransmission granularities.

[0047] Based on the transmission status feedback, it is determined whether there is a transmission interruption. If so, the interrupted data is retransmitted until a successful transmission confirmation is obtained.

[0048] The key to ensuring reliable data transmission, especially in unstable maritime satellite communication environments, lies in determining whether a transmission interruption exists based on the transmission status feedback. If so, the interrupted data is retransmitted until a successful transmission confirmation is obtained. This process is crucial. When the sending end receives transmission status feedback (e.g., no confirmation message received, NACK received, or confirmation message indicating packet loss), the system determines that a transmission interruption or data loss has occurred. At this point, the system identifies the untransmitted packets or batches and adds them back to the head of the priority transmission queue or a dedicated retransmission queue, immediately attempting to send them again. In another implementation, the system can employ a variant of the sliding window protocol. The sending end maintains a sending window, and the receiving end maintains a receiving window. When the receiving end detects packet loss or out-of-order delivery, it sends a Selective Repeat Request (SACK) to the sending end, specifying the specific packets that need to be retransmitted. The sending end retransmits only the lost packets based on the SACK, rather than the entire batch, thus improving retransmission efficiency. The retransmission process continues until the sending end receives a successful transmission confirmation from the target receiver for all data.

[0049] This invention effectively solves the problem of critical medical data transmission interruption caused by unstable satellite communication links at sea by introducing refined data identification, priority queue construction, and reliable transmission and retransmission mechanisms based on standardized data streams. Specifically, the system first performs deep analysis on the received standardized data stream, accurately identifying high-risk data markers through preset rules or intelligent algorithms. This identification process ensures that only information crucial to the patient's life is marked, avoiding unnecessary resource waste. Subsequently, based on these high-risk data markers, the system precisely extracts the corresponding data content and organizes it into a priority transmission queue. This queue design ensures that high-risk data receives the highest transmission priority, guaranteeing its priority scheduling and transmission within limited bandwidth resources. During data transmission, the system sends the data in the priority transmission queue in batches via the satellite communication link. This batch transmission strategy helps reduce the risk of single transmission failures and allows the system to monitor the transmission status of each batch of data in real time, thereby obtaining timely feedback on the transmission status. Once the system determines based on feedback that a transmission interruption or data loss has occurred, it immediately initiates the retransmission mechanism to resend the interrupted data. This retransmission process continues until the system receives confirmation of successful transmission of all data from the target receiver. Through these interconnected steps, the solution presented in this application forms a closed-loop, adaptive, and reliable data transmission system. Even in harsh marine communication environments, it can maximize the integrity and timeliness of high-risk medical data, thereby providing solid data support for remote medical emergency care.

[0050] The following is a concrete example. Suppose a crew member on an ocean-going vessel suffers a sudden heart attack. The ship's medical equipment collects real-time vital signs data such as electrocardiograms, blood pressure, and blood oxygen saturation, along with on-site video footage. After initial processing and standardization, this data forms a standardized data stream. This standardized data stream is sent to the ship's medical data gateway. Within this gateway, a data parsing module continuously monitors and parses the standardized data stream. This module has a built-in rule engine. For example, when it detects ST segment elevation in the electrocardiogram data or blood pressure data consistently below 90 / 60 mmHg, the rule engine immediately identifies and adds a "high-risk data identifier" to the corresponding data packet. Subsequently, a queue management module, based on these high-risk data identifiers, extracts data content, including electrocardiogram waveforms, blood pressure values, and associated on-site emergency video clips, from the standardized data stream and inserts it into a priority transmission queue called the "Emergency Medical Data Queue." Next, a satellite communication module retrieves data from the "Emergency Medical Data Queue" and divides it into, for example, 512KB data blocks. These data blocks are transmitted in batches via the ship's satellite antenna using the Inmarsat FleetBroadband satellite communication link, in an encrypted manner, to a remote medical center server on shore. After each batch of data is transmitted, the satellite communication module waits for an acknowledgment message from the remote medical center server. For example, if the remote medical center server does not return an acknowledgment message within 10 seconds, or if the acknowledgment message indicates that a certain data block has not been received, the ship's system determines that the transmission has been interrupted. At this point, the unacknowledged data block is added back to the head of the "emergency medical data queue," and transmission is attempted again. This retransmission process continues until the ship's system receives confirmation from the remote medical center server that all data blocks have been successfully received.

[0051] Through the above technical solution, this invention effectively addresses the challenge of unstable satellite communication links on ocean-going vessels, significantly improving the transmission reliability of critical data in remote emergency medical rescue. By meticulously analyzing standardized data streams and identifying high-risk data, it ensures that only the most urgent and critical medical information is prioritized. Constructing a priority transmission queue allows these high-risk data to receive priority transmission within limited bandwidth resources, guaranteeing the timeliness of information. More importantly, by sending data in batches and obtaining real-time transmission status feedback, combined with intelligent transmission interruption judgment and retransmission processing mechanisms, this application can minimize data loss due to communication interruptions, ensuring that high-risk medical data arrives completely and accurately at the target receiver. This greatly enhances the reliability of remote medical diagnosis and decision-making, buying valuable treatment time for patients with sudden acute illnesses at sea, thereby significantly improving the efficiency and success rate of emergency medical rescue on ocean-going vessels.

[0052] In this embodiment, the separation processing of the vital sign data and image information based on the integrity judgment result includes:

[0053] Based on the integrity judgment result, the format characteristics of the vital signs data and image information are identified.

[0054] Based on the aforementioned format characteristics, the vital signs data and image information are diverted to different processing channels.

[0055] For the vital signs data, extract the numerical fields to generate independent data units.

[0056] For the image information, extract the image metadata to generate the corresponding image unit.

[0057] The data units and image units are stored in a preset cache area respectively, awaiting subsequent classification processing.

[0058] This step aims to accurately identify the specific format type of the received vital sign data and imaging information based on the data integrity check results. This is crucial for subsequent correct parsing and processing. One implementation method is for the system to pre-define a format feature library, which contains identifiers or structural patterns of various common medical data formats (such as HL7, DICOM, FHIR, etc.). When a data stream is received, its exact format is identified by analyzing the header information, file extensions, or internal structural features of the data stream and comparing them with the feature library. Another implementation method is to utilize a machine learning model. By training on a large amount of medical data in different formats, the model can automatically learn and identify the characteristics of unknown or variant formats, thereby improving the accuracy and robustness of format identification. The purpose of this step is to guide different types of data to specialized processing paths based on the identified data formats to achieve efficient parallel processing. One implementation method is for the system to be configured with a data router or message queue system. After the format recognition module outputs the data format type, the router, according to preset routing rules, sends the vital sign data (e.g., identified as HL7 format) to a dedicated vital sign data parsing channel and the image information (e.g., identified as DICOM format) to a dedicated image processing channel. Another implementation approach is to adopt a microservice-based architecture, where different microservices are responsible for processing specific types of data. The format recognition result serves as a trigger condition, calling the corresponding microservice instance to process the split data, thereby achieving a modular and scalable data processing flow. This step aims to accurately separate numerical information with practical medical significance from the raw vital sign data and encapsulate it into independent units that are easy to process subsequently. One implementation approach is that, for structured vital sign data (such as HL7 messages), a specific parser or data mapping tool can be used to extract key numerical fields such as heart rate, blood pressure, blood oxygen saturation, and body temperature from the message according to predefined field specifications. These numerical fields, along with their corresponding measurement units and timestamps, can be encapsulated into a structured data object or record, i.e., an independent data unit. Another approach is to use Natural Language Processing (NLP) techniques or pattern matching algorithms to identify and extract numerical information from text descriptions for semi-structured or unstructured vital signs data. This information is then standardized to ensure that the generated data units have a uniform format. The purpose of this step is to extract key metadata describing the image content and attributes from the raw image information and organize it into independent image units for easy management and retrieval. One implementation method is to use a DICOM format medical image parser library to directly read metadata tags from the image file header, such as patient ID, examination date, image modality (CT, MRI, X-ray, etc.), image resolution, and pixel pitch. This metadata can be encapsulated into an image unit containing an image identifier and all relevant attributes.Another approach is to analyze image file attributes using image processing tools or extract descriptive information such as image type, shooting location, and anomalous area markers through manual annotation combined with machine learning for images of other non-DICOM formats. This information is then associated with the image file path or hash value to form image units. This step aims to provide temporary, efficient storage space for different types of data units to ensure that data can be quickly accessed and utilized in subsequent processing stages. One implementation method is to use a high-speed memory cache (such as RAM cache) or a temporary file system on a solid-state drive (SSD) as a pre-defined cache area. Vital feature data units and image units are written to their respective independent cache areas or file directories, along with timestamps and unique identifiers, so that subsequent processing modules can quickly retrieve and read them as needed. Another implementation method is to use a distributed caching system (such as a Redis cluster) or message queues (such as Kafka topics) to publish data units and image units as messages to different topics or queues. These cache areas or queues feature high throughput and low latency, effectively supporting the real-time data access needs of subsequent classification processing modules.

[0059] This invention effectively solves the problems of low data processing efficiency and information confusion in traditional methods by performing refined separation and processing of vital sign data and image information. Specifically, after receiving a data stream that has undergone integrity verification, the system first identifies the format features of these data streams. This process can accurately distinguish the specific structures and encoding methods of vital sign data and image information. Based on the identified format features, the system intelligently distributes the vital sign data and image information to different processing channels. This distribution mechanism ensures that different types of data can be processed efficiently in parallel by their respective specialized processing modules, avoiding bottlenecks and confusion that may occur with a single processing flow. In their respective processing channels, for vital sign data, the system further extracts key numerical fields, such as heart rate and blood pressure, and encapsulates this numerical information into independent, structured data units. Simultaneously, for image information, the system extracts its image metadata, such as patient information, image modality, and capture time, and generates corresponding image units. In this way, the raw, heterogeneous data is transformed into standardized, machine-processable independent units. Finally, these independent data units and image units are stored separately in preset caches. This caching mechanism not only provides high-speed data access capabilities but also ensures logical isolation between different types of data, providing a clear, orderly, and easily accessible data foundation for subsequent classification processing (such as prioritizing vital sign data in the initial classification results). Through the above series of steps, the proposed solution completes refined preprocessing and structured storage of data before it enters subsequent classification processing, greatly improving the efficiency and accuracy of data processing. This allows subsequent complex operations such as prioritization, anomaly detection, and correlation matching to be performed in a clear and standardized data environment, thereby providing faster and more reliable data support for satellite-based remote emergency medical rescue for ocean-going vessels.

[0060] As a specific implementation, suppose a medical device on an ocean-going vessel transmits a batch of emergency data via a satellite communication link, including an electrocardiogram (ECG) of a crew member and a chest X-ray. After the system completes the integrity assessment of this batch of data, it will obtain a result confirming the data integrity. At this point, the system will initiate a format feature recognition process based on this integrity assessment result. For example, the system may identify that the ECG data stream conforms to a specific message type in the HL7 (Health Level Seven) standard, while the chest X-ray data stream conforms to the DICOM (Digital Imaging and Communications in Medicine) standard. Based on these identified format features, the system will divert the HL7 formatted ECG data to a dedicated vital sign data parsing channel, while diverting the DICOM formatted chest X-ray data to a dedicated image information processing channel. In the vital sign data parsing channel, an HL7 parser will accurately extract numerical fields from the ECG data, such as heart rate (e.g., "88 beats / minute"), heart rhythm (e.g., "sinus rhythm"), ST segment offset, and other key physiological parameters. These extracted numerical fields, along with their timestamps and units of measurement, are encapsulated into individual data units, such as a JSON object or a database record. Simultaneously, in the image information processing channel, a DICOM parser extracts image metadata from the chest X-ray data, such as the patient's unique identifier, examination date, image modality ("CR" or "DR"), image resolution (e.g., "2048x2048 pixels"), and possible diagnostic descriptions. This metadata is encapsulated into a corresponding image unit, which may contain a reference to the storage location of the original image file. Finally, these generated individual data units (ECG values) and image units (X-ray metadata) are stored separately in pre-defined caches. For example, ECG value data units might be written to a high-speed memory queue, while X-ray image units might be stored in a temporary file storage area, with their metadata index written to another memory cache. This allows subsequent classification processing modules to quickly retrieve and process the corresponding data from these caches as needed.

[0061] Based on the above analysis, this invention effectively solves the problems of low data processing efficiency, data confusion, and difficulty in quickly extracting key information in traditional maritime emergency medical rescue due to the lack of specific data format recognition and diversion mechanisms. Specifically, by identifying the format characteristics of vital sign data and image information based on the integrity judgment results, the system can accurately distinguish different types of data, laying the foundation for subsequent professional processing and avoiding data misunderstanding and processing errors. Diverting data to different processing channels according to format characteristics enables parallel processing, significantly improving the overall efficiency of data preprocessing and shortening the time from data acquisition to an analyzable state. Extracting numerical fields from vital sign data and generating independent data units, and extracting image metadata from image information and generating corresponding image units, ensures the accurate extraction and structuring of key medical information, greatly facilitating subsequent prioritization, anomaly detection, and expert diagnosis. Storing these data units and image units separately in a preset cache not only optimizes data access speed but also ensures data isolation and rapid retrieval, providing an efficient and orderly data source for subsequent classification processing. This preprocessing mechanism ensures that the anomaly detection algorithm can analyze data based on clear and accurate numerical fields, reducing the risk of false positives and false negatives, and thus improving the reliability of high-risk data labeling. Ultimately, through efficient and accurate data separation and preparation, this solution significantly accelerates the entire remote emergency medical rescue process, enabling medical experts to obtain critical, high-quality patient information more quickly, thereby providing more timely and accurate medical support for emergency medical care on ocean-going vessels.

[0062] In this embodiment, the step of sending the data in the priority transmission queue to the target receiving end in batches via the satellite communication link includes:

[0063] For the priority transmission queue, determine the sending order and data packet size for each batch of data.

[0064] The data packets are encoded using an encrypted transmission protocol via the satellite communication link.

[0065] The encoded data packets are sent to the target receiving end, and the sending timestamp of each batch of data is recorded.

[0066] Based on the sending timestamp, the transmission delay is detected, and the sending frequency of subsequent data packets is adjusted.

[0067] Specifically, the transmission order and packet size of each batch of data are determined for the priority transmission queue to ensure orderly and efficient data transmission. The transmission order can be determined based on data priority, data type (e.g., vital signs data take precedence over image information), data volume, or the processing capacity of the target receiver. The packet size can be dynamically adjusted based on the bandwidth and latency characteristics of the satellite communication link, as well as the buffering capacity of the target receiver. For example, when bandwidth is limited, the packet size can be reduced to decrease the transmission time of a single packet. As another implementation, a time window-based transmission strategy can be adopted, packaging data within a certain time window into a batch and allocating different transmission time slots according to the importance of the data. The packet size can be preset to a fixed value or adaptively adjusted based on the current link's bit error rate and retransmission rate to optimize throughput.

[0068] Encoding data packets using encrypted transmission protocols via satellite communication links aims to ensure data transmission security and optimize data formats to suit the characteristics of satellite links. End-to-end encryption of data packets can be performed using TLS / SSL or IPsec protocols to ensure data is not intercepted or tampered with during transmission. Encoding processes can include data compression, channel coding (e.g., LDPC, Turbo codes), and interleaving techniques to improve data robustness and transmission reliability in noisy environments. Alternatively, proprietary encryption algorithms and data encapsulation formats can be employed, such as AES-based encryption and custom data frame structures. Encoding processes can also include forward error correction (FEC) coding, which adds redundant information at the transmitting end so that the receiving end can recover data without retransmission in the event of a few errors, thereby reducing the number of retransmissions and improving transmission efficiency.

[0069] The encoded data packets are sent to the target receiver, and a timestamp for each batch of data is recorded. This aims to provide a real-time time reference, facilitating the tracking of transmission status and the calculation of latency. The timestamp can be generated by a high-precision clock within the sending device and sent along with the data packets. Recording can be done by storing the timestamp in a local log file or memory, or by sending it to a monitoring system via a specific control channel. Alternatively, the timestamp can be synchronized using the Network Time Protocol (NTP) to ensure accuracy and consistency. Recording can be done using a distributed log system, associating the timestamp with the unique identifier of the data packet, the target receiver address, and other information for easy subsequent querying and analysis.

[0070] By detecting transmission delay based on the sending timestamp, the sending frequency of subsequent data packets is adjusted to identify the impact of environmental changes in real time and adaptively optimize the transmission strategy. Transmission delay can be calculated by comparing the receive timestamp with the sending timestamp in the acknowledgment (ACK) returned by the receiver. Adjusting the sending frequency can be based on a PID controller or a sliding window algorithm; when an increase in delay is detected, the sending frequency is reduced to avoid network congestion; when the delay decreases, the sending frequency is increased to fully utilize bandwidth. Alternatively, round-trip time (RTT) can be measured by periodically sending probe packets and used as an indicator of transmission delay. Adjusting the sending frequency can also employ strategies based on congestion control algorithms (e.g., TCP Vegas, TCP BBR), dynamically adjusting the sending window size based on delay and bandwidth utilization, thereby indirectly controlling the sending frequency. For example, when the delay exceeds a preset threshold, the sending frequency can be reduced exponentially or linearly; when the delay is below the threshold and the link is idle, the sending frequency can be gradually increased.

[0071] This invention improves the reliability and efficiency of data transmission in maritime environments by optimizing the batch data transmission process, enabling intelligent monitoring and dynamic adjustment of transmission delays. Specifically, the transmission order and data packet size of each batch of data are determined for the priority transmission queue, ensuring the orderliness and controllability of the transmission process and avoiding resource conflicts or inefficiencies caused by disordered transmission. Encoding data packets using an encrypted transmission protocol via the satellite communication link ensures data security while optimizing the data format to adapt to the characteristics of the satellite link, reducing the risk of interference during transmission. The encoded data packets are sent to the target receiver, and the transmission timestamp of each batch of data is recorded, providing a real-time time reference for accurate tracking of transmission status. Detecting transmission delays based on transmission timestamps allows for real-time identification of the impact of environmental changes, adjusting the transmission frequency of subsequent data packets accordingly. If delays increase, the frequency is reduced to alleviate congestion; if delays decrease, the frequency is increased to accelerate transmission, thus achieving adaptive optimization and effectively coping with the uncertainties of complex maritime environments. This approach, combined with the steps of identifying high-risk data and constructing a priority transmission queue, enables high-risk medical data to not only be prioritized during transmission but also to be dynamically adjusted based on real-time communication link conditions. This significantly improves the stability and efficiency of data transmission, thereby providing more reliable data support for maritime remote emergency medical rescue.

[0072] As a specific implementation method, high-priority vital sign data (e.g., electrocardiogram, blood oxygen saturation) can be prioritized over image information transmission. The data packet size can be dynamically adjusted based on the real-time bandwidth assessment of the current satellite link; for example, when the bandwidth is higher than 5 Mbps, the data packet size is set to 1500 bytes; when the bandwidth is lower than 5 Mbps, the data packet size is set to 500 bytes. During data packet transmission, encryption based on the TLS 1.3 protocol can be used, combined with LDPC (Low-Density Parity-Check) channel coding to enhance the data's anti-interference capability in weak signal environments. Before transmitting each data packet, the transmitting device (e.g., a shipborne satellite communication terminal) obtains the current UTC time from its internal high-precision clock and embeds it as a timestamp in the data packet header, while simultaneously recording the correspondence between the timestamp and the data packet ID in a local log file. After receiving the data packet, the receiving end (e.g., a shore-based medical center server) parses the transmission timestamp and immediately returns an acknowledgment message containing the reception timestamp. After receiving the acknowledgment message, the transmitting end calculates the round-trip time (RTT = reception timestamp - transmission timestamp). If the RTT of 5 consecutive data packets exceeds 2 seconds, the sending frequency of subsequent data packets will be reduced by 20%; if the RTT of 10 consecutive data packets is less than 1 second, the sending frequency will be increased by 10% until the preset maximum frequency is reached.

[0073] Through the above technical solution, this invention effectively addresses the dynamic transmission delays in complex maritime environments, significantly improving the reliability and efficiency of data transmission. This solution reduces data packet accumulation and retransmissions caused by delays, ensuring the timeliness and integrity of high-risk medical data. Simultaneously, encrypted transmission further enhances the security of medical data. Combined with the aforementioned scheme of identifying high-risk data and constructing a priority transmission queue, high-risk data in the priority transmission queue can be delivered more stably and efficiently, thereby further optimizing the overall emergency response speed and decision-making accuracy.

[0074] In this embodiment, storing transmission logs to a preset database for the successfully forwarded standardized data stream includes:

[0075] For the successfully forwarded standardized data stream, extract key field information from the transmission process.

[0076] The key field information is associated with the transmission timestamp to generate a transmission log record.

[0077] The transmission log is written to the preset database, and the write status feedback is obtained.

[0078] Specifically, after the standardized data stream is successfully forwarded via the satellite communication link, this method further refines the log storage mechanism to ensure the traceability and reliability of data transmission. The system accurately identifies and extracts key field information crucial for subsequent analysis from the successfully forwarded standardized data stream. These key fields are the core identifiers of data transmission events. Subsequently, the system associates this extracted key field information with the precise transmission timestamp of the successful data stream forwarding. This association operation integrates discrete data points into a complete transmission log record with a temporal context, ensuring that each data transmission event can be uniquely and accurately traced. Finally, the generated transmission log record is written to a pre-set database for persistent storage. During the writing process, the system actively obtains write status feedback from the database to confirm whether the log record has been successfully and completely stored. This series of steps works together to not only ensure the refinement, accuracy, and traceability of the transmission log but also effectively avoids data reliability issues caused by missing log records or storage failures by obtaining real-time write status feedback, thereby improving the data management efficiency and decision support capabilities of the entire remote emergency medical rescue system. In this way, even in maritime environments where satellite communication links may be unstable, a solid data foundation can be provided for subsequent data auditing, troubleshooting, and medical decision-making.

[0079] In one specific implementation, once the system successfully transmits a standardized data stream containing patient electrocardiogram (ECG) data and vital sign parameters to the onshore medical center via satellite communication, it immediately initiates a logging process. First, the system parses the successfully forwarded standardized data stream, extracting key field information. This includes, for example, the patient ID, data type (e.g., "ECG," "blood pressure"), unique transaction ID of the data packet, data generation time, and the IP address or identifier of the target receiver. For instance, a predefined JSON schema can be used to parse the data stream and extract field values ​​from specified paths. Next, the system obtains the system time of successful data stream forwarding, such as a Unix timestamp accurate to milliseconds. Then, the system combines these extracted key field information with the timestamp to generate a transmission log. For example, a JSON object can be constructed containing fields such as "patientId," "dataType," "transactionId," "dataGeneratedTime," "targetReceiver," and "transmissionTimestamp." Finally, the system uses a database connection pool to call the API of a preset database (e.g., a PostgreSQL database) and executes an SQL INSERT statement to write the JSON-formatted transmission log records to a table named "transmission_logs". After the write operation, the database returns a status code; for example, "200 OK" or the number of affected rows if the write is successful, and "500 Internal Server Error" or specific error information if the write fails. The system captures and parses this status code to confirm whether the log records have been successfully stored.

[0080] Based on the above analysis, this invention ensures the conciseness and accuracy of transmission log records, avoids interference from redundant information, and makes the log content more targeted. Simultaneously, by associating key field information with transmission timestamps, a clear temporal context is provided for each data transmission event, greatly enhancing log traceability and facilitating subsequent querying, auditing, and troubleshooting. More importantly, by obtaining write status feedback, the system can confirm in real time whether log records have been successfully stored, promptly detect and handle storage failures, thereby effectively avoiding missing log records and significantly improving data storage reliability and overall system stability. This is particularly crucial for satellite-based remote emergency medical rescue scenarios on ocean-going vessels, ensuring the integrity of critical medical data transmission records even in complex and variable communication environments, providing solid data support for medical decision-making and accountability.

[0081] In this embodiment, writing the transmission log record into the preset database and obtaining write status feedback includes:

[0082] The transmission log records are encapsulated using a preset storage format.

[0083] The encapsulated transmission log records are transmitted to the preset database via the database interface.

[0084] The storage space status of the preset database is detected to determine whether the write operation is complete.

[0085] Based on the write completion status, generate corresponding status feedback information and record it in the system log.

[0086] Specifically, the solution of this invention ensures the reliability and traceability of the log writing process by standardizing and encapsulating transmission log records, using a database interface for reliable transmission, actively detecting the database storage status, and accurately judging the write results, ultimately generating and recording detailed status feedback information. Specifically, firstly, the original transmission log records are encapsulated according to a preset unified format, enabling standardized processing of log data from different sources and of different types, laying a consistent foundation for subsequent transmission and storage. Then, through a standardized database interface, these encapsulated log records are securely and efficiently transmitted to a preset database. The stable connection and error handling mechanisms provided by the interface ensure the integrity of data transmission. Furthermore, before and after the write operation, the system actively checks the storage space status of the preset database, effectively avoiding write failures due to insufficient storage space, and confirms whether the data has been successfully persisted by accurately judging the write operation's return result. Finally, based on this write completion status, the system generates detailed and accurate status feedback information and records it in the system log, forming a complete operational loop. This mechanism not only solves the problem of inaccurate feedback due to write failures caused by insufficient storage space or transmission interruptions in traditional solutions, but also greatly improves the reliability, auditability, and troubleshooting efficiency of log storage by providing detailed log records, thus providing solid data support for satellite remote emergency medical rescue methods for ocean-going vessels.

[0087] As a specific implementation method, when the system needs to write the transmission log records of successfully forwarded standardized data streams into a preset database, the following steps can be followed. First, the transmission log records, including fields such as transmission time, packet ID, sender IP, receiver IP, transmission status (successful), and data size, are encapsulated in JSON format. Specifically, these fields can be organized into a JSON object, such as `{"timestamp":"2023-10-27T10:30:00Z", "packet_id":"XYZ123","sender_ip":"192.168.1.10","receiver_ip":"10.0.0.5","status":"success","data_size_bytes":1024}`. Then, through a database interface, such as using a JDBC driver in a Java application to connect to a PostgreSQL database, the encapsulated JSON format transmission log record is inserted as a new record into the `transmission_logs` table of the preset database. Before performing an insert operation, the system can call the PostgreSQL `pg_database_size()` function or query the `pg_stat_database` view to check the database's storage space status, such as checking if the available space is below a preset threshold (e.g., 10GB). After the insert operation is completed, the system checks the update count or transaction commit status returned by the JDBC connection to determine if the write was successful. If the update count is 1 and the transaction is successfully committed, the write is considered complete. Finally, based on the write completion status, corresponding status feedback information is generated, such as a JSON string containing `"status":"success"` and `"message":"Log entry successfully written"`, and it is recorded in the local file system's system log file (e.g., ` / var / log / app / system.log`) or sent to a centralized log management service.

[0088] Based on the above analysis, this invention effectively solves the problem of insufficient storage space or transmission interruption leading to write failures during traditional log writing, thus preventing accurate feedback on the write status. Specifically, by encapsulating the transmitted log records using a preset storage format, the consistency and standardization of log data are ensured, reducing the complexity and error rate of data processing. Transmission via a standardized database interface improves the stability and efficiency of data transmission. More importantly, by actively detecting the storage space status of the preset database, early warnings can be provided to avoid write failures due to insufficient storage space, significantly improving the success rate of log writing. Simultaneously, accurately determining the write completion status and generating detailed status feedback information, combined with system log records, makes the log writing process fully traceable and auditable, greatly enhancing the reliability of log storage. This is crucial for satellite-based remote emergency medical rescue methods for ocean-going vessels, ensuring the integrity and availability of critical transmission logs, providing a solid foundation for subsequent system maintenance, troubleshooting, and data analysis, thereby indirectly improving the stability and decision-making accuracy of the entire rescue system.

[0089] In this embodiment, the step of using an algorithm to detect anomalies and mark high-risk data for high-priority vital sign data in the preliminary classification results includes:

[0090] Based on the preliminary classification results, feature values ​​of high-priority vital signs data are extracted.

[0091] In this process, based on the preliminary classification results, feature values ​​of high-priority vital signs are extracted. The aim is to screen out the key indicators that best reflect the patient's physiological state or changes in their condition from a large dataset. For example, for electrocardiogram (ECG) data, feature values ​​may include heart rate, RR interval variability, and ST segment shift; for blood pressure data, feature values ​​may include systolic blood pressure, diastolic blood pressure, and pulse pressure; for blood oxygen saturation data, feature values ​​may include SpO2 value and its trend. These feature values ​​can be extracted using various techniques. For instance, signal processing techniques (such as Fourier transform and wavelet analysis) can be used to extract frequency or time domain features from the original waveform data; statistical methods can also be used to calculate the mean, variance, peak value, and slope of the data.

[0092] Abnormal data points are identified by pattern matching of the feature values ​​using a preset algorithm.

[0093] The process of using a preset algorithm to perform pattern matching on the feature values ​​and identify abnormal data points is to determine whether the extracted feature values ​​deviate from the normal physiological range or warning threshold. The preset algorithm can include rule-based expert systems, for example, defining a heart rate exceeding 120 beats / minute or falling below 50 beats / minute as abnormal; it can also employ machine learning algorithms, such as support vector machines (SVM), decision trees, and neural networks, to learn patterns by training on historical normal and abnormal data, and then classify new feature values. Furthermore, statistical process control (SPC) methods, such as Shewhart control charts or EWMA control charts, can be used to monitor fluctuations in feature values ​​and identify abnormal points exceeding control limits.

[0094] For the abnormal data points, add a high-risk identifier and generate a marked record.

[0095] The purpose of adding high-risk identifiers and generating tagged records for the aforementioned abnormal data points is to clearly identify which data points pose a potential danger and provide a basis for subsequent processing. The high-risk identifier can be a Boolean value (such as "true" or "false") or a risk level (such as "high," "medium," or "low"). The tagged record can include the timestamp of the abnormal data point, the specific feature value, the detected anomaly type, the risk level, and the rule or model output that triggered the anomaly. For example, a JSON-formatted record can be generated, containing fields such as "timestamp," "feature_name," "feature_value," "anomaly_type," and "risk_level."

[0096] The marked records are integrated into an anomaly mark set and stored in a temporary cache.

[0097] The integration of these flagged records into an anomaly flag set, stored in a temporary cache, facilitates unified management and rapid access to all detected anomalies. The anomaly flag set can be a data structure such as a list, array, or hash table, containing multiple independent flagged records. The temporary cache can be a region in memory, such as RAM, or a temporary file on a high-speed solid-state drive (SSD), characterized by high read / write speeds to meet real-time processing requirements. This storage method ensures that in emergency situations, all high-risk data can be quickly retrieved and processed, providing a timely data source for subsequent correlation matching and prioritized transmission.

[0098] The solution of this invention, through the aforementioned steps, focuses on high-priority vital sign data after receiving the preliminary classification results. By precisely extracting feature values, it avoids blindly processing all data, thus significantly improving detection efficiency. Subsequently, a preset algorithm is used to perform pattern matching on these feature values, accurately identifying abnormal data points that deviate from the normal range, effectively reducing the risk of false alarms and missed alarms. Once an anomaly is identified, the system immediately adds a high-risk marker and generates detailed marking records, ensuring that every potential danger signal is clearly recorded. Finally, these marking records are integrated and stored in a temporary cache, forming an easily managed and quickly accessible set of anomaly markers, providing timely and reliable data support for subsequent emergency handling procedures. This mechanism, combined with the aforementioned prioritization of vital sign data, enables the system to prioritize the most critical medical data and detect and mark potential emergencies at the first opportunity, thereby gaining valuable time for remote emergency medical rescue on ocean-going vessels.

[0099] One specific implementation method is as follows: After receiving the preliminary classification results, the system first calls a "feature extractor" module. For electrocardiogram (ECG) data, this module uses QRS complex detection based on the Pan-Tompkins algorithm and calculates feature values ​​such as heart rate and RR interval variability; for blood oxygen saturation data, it directly extracts SpO2 value and pulse rate. These extracted feature values ​​are then fed into an "anomaly detector" module. This module can pre-train an anomaly detection model based on a Long Short-Term Memory (LSTM) network. This model learns the time-series patterns of a large amount of normal physiological data and can determine in real time whether the current feature value sequence deviates from the normal pattern. For example, when the heart rate fluctuates drastically in a short period or the SpO2 value remains below 90%, the model outputs an anomaly score. If the anomaly score exceeds a preset threshold, the data point is identified as an anomaly. Subsequently, the "risk marker" module adds a "high-risk" label to the anomalous data point and generates a marker record containing time, feature type, anomaly value, risk level, and detection model confidence. For example, a record might be `{"time": "2023-10-27 10:30:05","feature": "heart_rate", "value": "135bpm", "risk_level": "high", "confidence": "0.98"}`. Finally, these tagged records are added to a dynamic array and stored in the server's memory cache, awaiting further processing by the "Federated Data Group Generation Module".

[0100] Through the above technical solution, this invention can efficiently and accurately identify and mark abnormal data points from high-priority vital sign data, effectively solving the problems of delay and insufficient accuracy in anomaly detection in traditional methods. This mechanism ensures that in emergency medical rescue scenarios on ocean-going vessels, the critical condition of patients can be detected in a timely manner, providing crucial and highly reliable information support for subsequent medical decisions and interventions, thereby significantly improving the response speed and success rate of remote emergency care.

[0101] In this embodiment, transmitting the encapsulated transmission log record to the preset database via the database interface includes:

[0102] For the encapsulated transmission log records, determine the transmission priority.

[0103] The transmission log records are sent to the preset database via the database interface using a batch transmission method.

[0104] Detect data integrity during transmission and record transmission status.

[0105] Based on the transmission status, a transmission completion confirmation message is generated, and the system log record is updated.

[0106] Specifically, the solution of this invention effectively solves the problems of priority confusion, inefficiency, data corruption risk, and lack of status feedback that may occur during log transmission in complex maritime environments by refining the process of log recording. Specifically, it determines the transmission priority for the encapsulated log records, ensuring that critical logs can be identified and processed first, avoiding delays in important information due to improper transmission order; it sends log records in batches through a database interface, improving overall transmission efficiency and reducing the resource consumption of multiple individual transmissions; it detects data integrity during transmission and records the transmission status, ensuring the accuracy and reliability of log data during transmission, while also enabling real-time monitoring of transmission progress; it generates transmission completion confirmation information based on the transmission status and updates the system log records, establishing a closed-loop feedback mechanism to ensure that each transmission result is traceable and that the system log reflects the latest status in a timely manner. These features work together to enhance the stability, efficiency, and controllability of log transmission.

[0107] In the aforementioned satellite-based remote emergency medical rescue method for ocean-going vessels, successfully forwarded standardized data streams require storage of transmission logs in a pre-set database and acquisition of storage confirmation information. Building upon this, this solution further optimizes the process of writing log records to the pre-set database. By prioritizing transmission log records, it ensures that important log information is processed and transmitted preferentially under limited satellite communication resources, which is crucial for timely understanding of system operation status and potential risks. Batch transmission significantly improves log writing efficiency, reducing resource waste and delays caused by frequent small data packet transmissions, especially on high-latency, low-bandwidth satellite links, where its advantages are even more pronounced. A data integrity detection mechanism ensures the reliability of log data, preventing the loss or damage of critical information due to transmission errors, thus ensuring the accuracy of stored logs. Finally, the generation of transmission completion confirmation information and the updating of system logs construct a reliable feedback loop, making the entire log storage process traceable and auditable, greatly improving the robustness and reliability of the entire remote emergency medical rescue system in terms of log management.

[0108] As a specific implementation method, when the system needs to transmit encapsulated transmission log records to a preset database, it can first prioritize these log records. For example, the system can classify them into three priority levels: "urgent," "warning," and "information," based on their type or content. For instance, logs related to satellite communication link interruptions or medical equipment malfunctions can be marked as "urgent," while regular data transmission success logs are marked as "information." Subsequently, the system sends these log records to the preset database via a batch transmission method through the database interface. Specifically, a batch size threshold can be set, such as packaging all currently accumulated log records into a data batch for transmission every 50 accumulated log records, or every 30 seconds (whichever comes first). Before transmission, the system can calculate a CRC32 checksum for the data batch and append this checksum to the batch. During the transmission of the data batch to the preset database via the satellite communication link, the system continuously monitors the transmission status, such as monitoring network connection stability and timely arrival of data packets. When the preset database receives the data batch, it recalculates its CRC32 checksum and compares it with the received checksum to check data integrity. If the checksum matches, the data is considered complete; otherwise, it is recorded as corrupted. The system records these detection results, including whether the transmission was successful and whether there was data corruption, as transmission status. Finally, based on the recorded transmission status, the system generates corresponding transmission completion confirmation information. For example, if the data is complete and successfully written to the database, a confirmation message of "Batch ID: XXXX, Status: Successfully Written" is generated; if the data is corrupted or the write failed, a confirmation message of "Batch ID: XXXX, Status: Write Failed, Error Code: YYYY" is generated. These confirmation messages are then appended to the system's own operation log file so that administrators can view the detailed transmission information at any time.

[0109] Based on the above analysis, this invention effectively solves the problems of lack of priority management, low efficiency, difficulty in ensuring data integrity, and untimely and incomplete status feedback during log transmission. By prioritizing transmitted log records, it ensures that critical and urgent log information is transmitted and processed first, avoiding the loss of optimal processing opportunities due to transmission delays. The batch transmission method significantly improves the efficiency of writing logs to the preset database and reduces unnecessary communication overhead, especially in environments with limited bandwidth and high latency in satellite communication links, enabling more efficient use of communication resources. The introduction of a data integrity detection mechanism greatly ensures the accuracy and reliability of log data during transmission, avoiding information distortion caused by data corruption or loss, thereby ensuring the authenticity and validity of stored logs. Furthermore, generating completion confirmation information and updating system log records based on transmission status constructs a reliable feedback loop, making the log transmission process transparent and traceable. This significantly improves the robustness and controllability of the entire remote emergency medical rescue system in terms of log management, providing a solid data foundation for subsequent system maintenance, troubleshooting, and performance optimization.

[0110] Example 2, Figure 2 This is a schematic diagram of a satellite-based remote emergency medical rescue system for ocean-going vessels, as shown in Embodiment 2 of the present invention. Figure 2As shown, Embodiment 2 provides a satellite-based remote emergency medical rescue system for ocean-going vessels, based on the satellite-based remote emergency medical rescue method for ocean-going vessels described in Embodiment 1. The system includes: an integrity judgment module 201, a classification result acquisition module 202, an anomaly marker set formation module 203, a joint data group generation module 204, a standardized data stream acquisition module 205, a transmission status recording module 206, and a confirmation information acquisition module 207. The integrity judgment module 201 acquires real-time vital sign data and image information from medical devices via a satellite communication link, performs format verification on the vital sign data and image information using a preset access protocol, and determines the integrity of the vital sign data and image information. The classification result acquisition module 202 separates the vital sign data and image information according to the integrity judgment result, prioritizes the vital sign data using classification rules, and obtains a preliminary classification result. The anomaly marker set formation module 203 uses an algorithm to detect anomalies in the high-priority vital sign data in the preliminary classification result, marks high-risk data, and forms an anomaly marker set. The joint data set generation module 204 is used to associate and match the high-risk data with the corresponding image information according to the anomaly marker set to generate a joint data set. The standardized data stream obtaining module 205 is used to unify the format of the vital sign data and image information using standardized conversion rules for the joint data set to obtain a standardized data stream. The transmission status recording module 206 is used to generate a priority transmission queue for the high-risk data portion of the standardized data stream, forward it through the satellite communication link, and record the transmission status. The confirmation information acquisition module 207 is used to store the transmission log to a preset database for the successfully forwarded standardized data stream and obtain the storage confirmation information.

[0111] The various variations and specific examples of the satellite remote emergency medical rescue method for ocean-going vessels provided in Embodiment 1 are also applicable to the satellite remote emergency medical rescue system for ocean-going vessels provided in this embodiment. Through the foregoing detailed description of a satellite remote emergency medical rescue method for ocean-going vessels, those skilled in the art can clearly understand the implementation method of the satellite remote emergency medical rescue system for ocean-going vessels in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0112] Example 3, Figure 3 This is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present invention, as shown below. Figure 3 As shown, Embodiment 3 also provides an electronic device 300, which may include a processor 301 and a memory 302.

[0113] Memory 302 is used to store programs. Memory 302 may include volatile memory, such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.; memory may also include non-volatile memory, such as flash memory. Memory 302 is used to store computer programs (such as application programs, functional modules, etc. that implement the above methods), computer instructions, etc. The computer programs, computer instructions, etc., can be partitioned and stored in one or more memories 302. Furthermore, the computer programs, computer instructions, data, etc., can be accessed by processor 301.

[0114] The aforementioned computer programs and instructions can be stored in one or more partitions of memory 302. Furthermore, the aforementioned computer programs and instructions can be invoked by processor 301.

[0115] The processor 301 is configured to execute the computer program stored in the memory 302 to implement the various steps in the methods described in the above embodiments.

[0116] For details, please refer to the relevant descriptions in the preceding method embodiments.

[0117] The processor 301 and the memory 302 can be independent structures or integrated structures. When the processor 301 and the memory 302 are independent structures, the memory 302 and the processor 301 can be coupled together via bus 303.

[0118] The electronic device in this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principle are the same, and will not be repeated here.

[0119] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A satellite-based remote emergency medical rescue method for ocean-going vessels, characterized in that, include: Real-time vital signs data and image information are acquired from medical devices via satellite communication links. The format of the vital signs data and image information is verified using a preset access protocol to determine the integrity of the vital signs data and image information. Based on the integrity judgment result, the vital signs data and image information are separated and processed, and the vital signs data are prioritized according to classification rules to obtain a preliminary classification result. For the high-priority vital sign data in the preliminary classification results, an algorithm is used to detect anomalies, mark high-risk data, and form an anomaly label set; Based on the set of anomaly markers, the high-risk data is associated and matched with the corresponding image information to generate a joint data group; For the aforementioned combined data set, standardized conversion rules are used to unify the format of the vital sign data and image information to obtain a standardized data stream; Based on the standardized data stream, a priority transmission queue is generated for the high-risk data portion, which is then forwarded through the satellite communication link, and the transmission status is recorded. For the standardized data stream that is successfully forwarded, the transmission log is stored in a preset database, and storage confirmation information is obtained.

2. The satellite-based remote emergency medical rescue method for ocean-going vessels according to claim 1, characterized in that, The step of generating a priority transmission queue for high-risk data portions based on the standardized data stream and forwarding it via the satellite communication link includes: For the standardized data stream, the data fields are parsed to identify high-risk data identifiers; Based on the high-risk data identifier, extract the corresponding data content and construct a priority transmission queue; The data in the priority transmission queue is sent to the target receiving end in batches through the satellite communication link, and the transmission status feedback of each batch of data is obtained. Based on the transmission status feedback, it is determined whether there is a transmission interruption. If so, the interrupted data is retransmitted until a successful transmission confirmation is obtained.

3. The satellite-based remote emergency medical rescue method for ocean-going vessels according to claim 1, characterized in that, The step of separating the vital sign data and image information based on the integrity judgment result includes: Based on the integrity assessment result, identify the format characteristics of the vital sign data and image information; Based on the aforementioned format characteristics, the vital sign data and image information are distributed to different processing channels; For the vital signs data, extract the numerical fields to generate independent data units; For the image information, extract the image metadata and generate the corresponding image unit; The data units and image units are stored in a preset cache area respectively, awaiting subsequent classification processing.

4. The satellite-based remote emergency medical rescue method for ocean-going vessels according to claim 2, characterized in that, The step of transmitting data in the priority transmission queue to the target receiving end in batches via the satellite communication link includes: For the priority transmission queue, determine the sending order and data packet size for each batch of data; The data packets are encoded using an encrypted transmission protocol via the satellite communication link. The encoded data packets are sent to the target receiving end, and the sending timestamp of each batch of data is recorded. Based on the sending timestamp, the transmission delay is detected, and the sending frequency of subsequent data packets is adjusted.

5. The satellite-based remote emergency medical rescue method for ocean-going vessels according to claim 1, characterized in that, The step of storing transmission logs to a preset database for the successfully forwarded standardized data stream includes: For the successfully forwarded standardized data stream, extract key field information from the transmission process; Associate the key field information with the transmission timestamp to generate a transmission log record; The transmission log is written to the preset database, and the write status feedback is obtained.

6. The satellite-based remote emergency medical rescue method for ocean-going vessels according to claim 5, characterized in that, The step of writing the transmission log record to the preset database and obtaining write status feedback includes: The transmission log records are encapsulated using a preset storage format; The encapsulated transmission log records are transmitted to the preset database via the database interface; Detect the storage space status of the preset database to determine whether the writing is complete; Based on the write completion status, generate corresponding status feedback information and record it in the system log.

7. The satellite-based remote emergency medical rescue method for ocean-going vessels according to claim 1, characterized in that, For the high-priority vital sign data in the preliminary classification results, an algorithm is used for anomaly detection, and high-risk data is marked, including: Based on the preliminary classification results, feature values ​​of high-priority vital sign data are extracted; Abnormal data points are identified by pattern matching of the feature values ​​using a preset algorithm. For the aforementioned abnormal data points, add a high-risk identifier and generate a marked record; The marked records are integrated into an anomaly mark set and stored in a temporary cache.

8. The satellite-based remote emergency medical rescue method for ocean-going vessels according to claim 6, characterized in that, The step of transmitting the encapsulated transmission log record to the preset database via the database interface includes: For the encapsulated transmission log records, determine the transmission priority; The transmission log records are sent to the preset database via the database interface using a batch transmission method. Detect data integrity during transmission and record transmission status; Based on the transmission status, a transmission completion confirmation message is generated, and the system log record is updated.

9. A satellite-based remote emergency medical rescue system for ocean-going vessels, based on the satellite-based remote emergency medical rescue method for ocean-going vessels as described in any one of claims 1-8, characterized in that, The system includes: The integrity judgment module is used to acquire real-time vital sign data and image information from medical devices through a satellite communication link, and to perform format verification on the vital sign data and image information using a preset access protocol to determine the integrity of the vital sign data and image information. The classification result acquisition module is used to separate the vital sign data and image information according to the completeness judgment result, and to prioritize the vital sign data according to the classification rules to obtain a preliminary classification result. The anomaly label set formation module is used to perform anomaly detection using an algorithm on the high-priority vital sign data in the preliminary classification results, label high-risk data, and form an anomaly label set. The joint data group generation module is used to associate and match the high-risk data with the corresponding image information based on the anomaly marker set to generate a joint data group; The standardized data stream acquisition module is used to unify the format of the vital sign data and image information using standardized conversion rules for the joint data set, thereby obtaining a standardized data stream. The transmission status recording module is used to generate a priority transmission queue for the high-risk data portion of the standardized data stream, forward it through the satellite communication link, and record the transmission status. The confirmation information acquisition module is used to store transmission logs to a preset database and acquire storage confirmation information for the successfully forwarded standardized data stream.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the satellite remote emergency medical rescue method for ocean-going vessels as described in any one of claims 1-8.

Images