A method and system for communication of crew monitoring data

Abstract

This invention discloses a communication method and system for crew monitoring data. The method includes: real-time acquisition of various types of crew monitoring data through sensors; determining indicator parameters for each monitoring data based on data characteristics; calculating the importance weight of each crew monitoring data, wherein the importance weight guides the dynamic adjustment of corresponding quantization levels and bandwidth allocation; determining an adaptive quantization level based on the importance weight of each crew monitoring data and the current bandwidth situation, and dynamically allocating bandwidth resources for each data stream; and quantifying various types of crew monitoring data according to the aforementioned importance weight and adaptive quantization level. This invention improves the efficiency and reliability of crew monitoring data transmission by dynamically assessing data importance and optimizing quantization and bandwidth allocation, ensuring priority transmission of critical data, saving bandwidth resources, and enhancing the real-time performance and stability of system data transmission.

Description

Technical Field

[0001] This invention belongs to the field of computer technology, and in particular relates to a communication method and system for monitoring crew data. Background Technology

[0002] With the rapid development of the global shipping industry, shipping plays a vital role in international trade. However, the complexity of the marine environment and the harshness of operating conditions place higher demands on the health and safety of crew members. To ensure the safety and work efficiency of crew members, crew monitoring systems have emerged. These systems use various sensors installed on ships to collect real-time physiological indicators and environmental data from crew members, enabling comprehensive monitoring of their health status and working environment.

[0003] Existing crew monitoring systems rely on wireless communication technology for data transmission. These systems typically employ fixed communication protocols and bandwidth allocation strategies to transmit collected monitoring data in real time to a central processing unit or cloud platform for storage and analysis. However, the wireless communication environment on ships is complex, with signals limited by the ship's structure and the marine environment, resulting in limited communication bandwidth. Under high load conditions, limited bandwidth resources struggle to meet the real-time transmission demands of large amounts of monitoring data, easily leading to data congestion and transmission delays.

[0004] Furthermore, different types of monitoring data have varying degrees of importance and urgency. The existing system lacks an effective prioritization mechanism, failing to ensure the timely transmission of critical data and potentially leading to delays or loss of important information.

[0005] Existing systems are mostly statically configured, lacking intelligent decision-making and adaptive capabilities. They cannot automatically optimize data transmission strategies based on real-time monitoring data and network conditions, resulting in insufficient adaptability and robustness of the system in dynamic environments.

[0006] Therefore, there is an urgent need for a communication method that can intelligently assess the importance of monitoring data and dynamically optimize quantification and bandwidth allocation to improve the efficiency and reliability of crew monitoring data transmission, ensure the priority transmission of critical data, optimize the utilization of bandwidth resources, and enhance the performance of the entire monitoring system and the level of crew safety. Summary of the Invention

[0007] To address the shortcomings of the existing technology, the present invention provides a communication method for crew monitoring data, the method comprising:

[0008] Various types of crew monitoring data are collected in real time through sensors, and the index parameters of each monitoring data are determined based on the data characteristics.

[0009] The importance weights of each crew monitoring data point are calculated, and these importance weights are used to guide the dynamic adjustment of the corresponding quantification level and bandwidth allocation.

[0010] The adaptive quantification level is determined based on the importance weight of each crew monitoring data and the current bandwidth situation, and the bandwidth resources of each data stream are dynamically allocated.

[0011] Based on the importance weights and adaptive quantification levels of the aforementioned monitoring data, the various types of crew monitoring data are quantified.

[0012] In one embodiment, the indicator parameters include data criticality, data change rate, anomaly probability, time sensitivity, and data dependency.

[0013] In one embodiment, based on the determined quantization level of each monitoring data, the system partitions the monitoring data, with each partition corresponding to a transmission buffer.

[0014] In one embodiment, monitoring data with the same quantization level are assigned to the same transmission buffer, and each transmission buffer is dedicated to storing data within the same quantization level range.

[0015] In one embodiment, multiple partitions are defined for transmitting buffers based on quantization levels, wherein low quantization levels correspond to high-precision transmitting buffers and high quantization levels correspond to low-precision transmitting buffers.

[0016] In one embodiment, the data in each transmit buffer is compressed accordingly;

[0017] The data compression algorithms used in the multiple send buffers are not exactly the same.

[0018] In one embodiment, the data compression process is completed in collaboration between hardware-level compression acceleration and the processor of the data processing unit (DPU).

[0019] Among them, the compression accelerator executes the selected compression algorithm and processes data compression in parallel. The compression module software on the DPU dynamically selects and directs the compression accelerator to execute the corresponding compression task according to the quantization level of the send buffer.

[0020] The compressed data is returned via a high-speed storage interface and stored back in the corresponding send buffer.

[0021] In one embodiment, the bandwidth allocated to each transmit buffer is calculated as the sum of the bandwidth resources allocated to all monitoring data within that transmit buffer.

[0022] In one embodiment, during transmission, the system starts transmitting data from the buffer containing the monitoring data with the highest bandwidth allocated among all monitoring data.

[0023] The system sorts the transmission buffers according to the bandwidth allocation of the monitored data, and generates a transmission queue for the buffer area;

[0024] The communication interface module extracts compressed data from the buffer with the highest bandwidth allocation in sequence according to the transmission queue and transmits it.

[0025] The hardware layer communication interface module reads data from the send buffer through the DMA engine and sends the data to the central monitoring system through the physical layer interface.

[0026] The present invention also provides a communication system for monitoring crew data, the system including a memory and a processor, the memory storing a computer program, and the processor executing the computer program stored in the memory to implement the aforementioned method.

[0027] The communication method for crew monitoring data provided by this invention collects various types of crew monitoring data in real time and determines key indicator parameters based on data characteristics, such as data criticality, data change rate, anomaly probability, time sensitivity, and data dependency, to accurately calculate the importance weight of each monitoring data point. This weight guides the dynamic adjustment of quantification levels and bandwidth allocation, enabling the system to adaptively determine the optimal quantification level and bandwidth resource allocation strategy based on real-time data importance and current bandwidth conditions. By dynamically quantifying various types of monitoring data, this invention significantly improves the efficiency and reliability of data transmission, ensuring that critical data is prioritized for transmission even when network bandwidth is limited, thus reducing bandwidth waste. Simultaneously, the dynamic adjustment mechanism enhances the system's adaptability to changes in network conditions, improving the stability and response speed of the monitoring system in complex marine environments. Attached Figure Description

[0028] The above and other objects, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the present disclosure are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein:

[0029] Figure 1 This is a flowchart illustrating a communication method for crew monitoring data according to an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0031] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0032] It should be understood that although the terms first, second, third, etc., may be used to describe... in the embodiments of the present invention, these... should not be limited to these terms. These terms are only used to distinguish... For example, first... may also be referred to as second... without departing from the scope of the embodiments of the present invention, and similarly, second... may also be referred to as first...

[0033] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0034] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0035] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0036] Existing crew monitoring systems face several technical challenges in data communication. First, crew monitoring data is diverse, including various types and levels of physiological and behavioral data. Traditional communication methods lack effective prioritization mechanisms, making it difficult to ensure the real-time transmission and processing of critical data. Second, network bandwidth resources are limited, especially in the complex and variable wireless communication environment of the ocean, leading to low data transmission efficiency under high loads, severely impacting the overall performance and reliability of the monitoring system. Furthermore, existing methods often employ fixed quantization levels and bandwidth allocation strategies, failing to dynamically adapt to changes in data characteristics and network conditions. This results in wasted bandwidth resources or loss of critical data, affecting the timeliness and accuracy of crew safety monitoring.

[0037] like Figure 1 As shown, the present invention provides a communication method for crew monitoring data, the method comprising:

[0038] Various types of crew monitoring data are collected in real time through sensors.

[0039] The indicator parameters for each monitoring data are determined based on the data characteristics, including data criticality, data change rate, anomaly probability, time sensitivity, and data dependence.

[0040] Calculate the importance weight W of each crew monitoring data point. i (t), where W represents the importance weight of each crew monitoring data point. i (t) is used to guide the dynamic adjustment of the corresponding quantization level and bandwidth allocation.

[0041] Based on the importance weight of each crew monitoring data W i (t) and the current bandwidth conditions determine the adaptive quantization level Q. i (t); and dynamically allocate bandwidth resources for each data stream.

[0042] Based on the importance weights W of the aforementioned monitoring data i (t) and adaptive quantization level Q i (t) quantifies various types of crew monitoring data.

[0043] The communication method for crew monitoring data provided by this invention collects various types of crew monitoring data in real time and determines key indicator parameters based on data characteristics, such as data criticality, data change rate, anomaly probability, time sensitivity, and data dependency, to accurately calculate the importance weight of each monitoring data point. This weight guides the dynamic adjustment of quantification levels and bandwidth allocation, enabling the system to adaptively determine the optimal quantification level and bandwidth resource allocation strategy based on real-time data importance and current bandwidth conditions. By dynamically quantifying various types of monitoring data, this invention significantly improves the efficiency and reliability of data transmission, ensuring that critical data is prioritized for transmission even when network bandwidth is limited, thus reducing bandwidth waste. Simultaneously, the dynamic adjustment mechanism enhances the system's adaptability to changes in network conditions, improving the stability and response speed of the monitoring system in complex marine environments.

[0044] In one embodiment, the crew monitoring system collects various types of data, including physiological parameters (such as heart rate and blood pressure), location data, and environmental parameters (such as temperature and humidity). These data exhibit different levels of criticality and dynamic characteristics during ship operation. To efficiently manage this data, this invention first performs multi-dimensional modeling of the system, defining various parameters to quantify the importance of the data and transmission requirements.

[0045] In one embodiment, indicator parameters are determined based on data characteristics, including data criticality, data change rate, anomaly probability, time sensitivity, and data dependency, specifically:

[0046] Among them, data is critical (C) i (t) measures the importance of data i at time t, and is set according to the data type and crew safety requirements. For example, vital signs data are more important than environmental parameters. Criticality can be quantified according to pre-set levels or expert assessments, and the value range is usually [0,1], with higher values ​​indicating more critical data.

[0047] For example, a specific definition could be:

[0048]

[0049] Among them, the rate of change of data V i (t) reflects the rate of change of data i over time t, and is used to measure the dynamic nature of the data. Rate of change V i The formula for calculating (t) is:

[0050]

[0051] Parameter definition:

[0052] V i (t): The rate of change of data i over time t.

[0053] D i (t): The value of data i at time t.

[0054] Δt: Time step, representing the time interval between two adjacent samples.

[0055] ε: A small constant to prevent division by zero, usually taken as a very small value (e.g., 10). -6 ).

[0056] Furthermore, to ensure that the rate of change is within the range [0,1], a normalization function is defined: V max This is a predefined maximum acceptable rate of change; any rate of change exceeding this value will be truncated to 1.

[0057] Wherein, the anomaly probability A i (t) represents the probability that data i will exhibit an anomaly at time t. This probability can be evaluated in real time using machine learning models or statistical methods, such as building an anomaly detection model using historical data to calculate the anomaly probability of the current data point in real time.

[0058] Anomaly probability A i (t) The probability of an anomaly occurring in data i at time t is evaluated in real time using machine learning models or statistical methods. Anomaly detection techniques (such as those based on support vector machines, neural networks, or time series analysis) are used to calculate the anomaly probability.

[0059] For example: A i (t) = AnomalyDetection(D i (t) . Here, AnomalyDetection(·) represents a specific anomaly detection algorithm, which outputs the anomaly probability of data i at time t, in the range [0,1].

[0060] Among them, time sensitivity T i (t) represents the sensitivity of data i to transmission delay, which is set according to the application scenario of the data. For data that needs to be monitored in real time, such as heart rate, the time sensitivity is high; for data that changes slowly, such as cabin temperature, the time sensitivity is relatively low. The time sensitivity is usually taken in the range of [0,1].

[0061] The definition of time sensitivity is as follows:

[0062]

[0063] Among them, data dependency D ij(t) describes the degree of correlation between data i and data j at time t, determined through correlation analysis or causal relationship modeling. Data dependency reflects the need for joint analysis of certain data; data with high dependency may require synchronous transmission.

[0064] Data Dependency D ij (t) describes the degree of correlation between data i and data j at time t, determined through correlation analysis or causal relationship modeling. Data dependency reflects the need for joint analysis of certain data; data with high dependency may require synchronous transmission. The formula is defined as:

[0065] D ij (t)=ρ ij (t).

[0066] Where, ρ ij (t) is the correlation coefficient between data i and data j at time t, calculated using the Pearson correlation coefficient or other appropriate statistical correlation measures, and ranges from [0,1].

[0067] In one embodiment, to comprehensively evaluate the transmission priority of each data point, an importance weight W for each monitoring data point is defined for calculation. i (t). This weight comprehensively considers the criticality of the data, rate of change, probability of anomalies, time sensitivity, and its dependence on other data. The importance weight W for each crew monitoring data point is calculated. i The specific formula for calculating (t) is as follows:

[0068]

[0069] Where α1, α2, α3, and α4 are the weight coefficients for each dimension, satisfying α1 + α2 + α3 + α4 = 1; the functions f(·), g(·), h(·), and k(·) are the normalization functions for criticality, rate of change, probability of anomalies, and time sensitivity, respectively. The normalization functions are used to map data of different magnitudes to a uniform range; β ij This is the data dependency weighting coefficient, reflecting the importance of the relationship between data points, and β... ij It dynamically adjusts over time to adapt to changes in system state.

[0070] In one embodiment, the importance weight W of each crew monitoring data point is... i (t) is used to guide the corresponding quantitative level, including the importance weight W based on each crew monitoring data point. i (t) and the current bandwidth conditions determine the adaptive quantization level Q. i (t), specifically including:

[0071] Based on the importance weights W of each monitoring data point i(t) Determine the adaptive quantization level Q i (t) to optimize data compression and transmission efficiency.

[0072] The formula for adjusting the quantification level is as follows:

[0073]

[0074] Among them, W i (t) represents the importance weight of any item in the crew monitoring data, n is the number of monitoring data items, and Q min and Q max These represent the minimum and maximum quantization levels, respectively; γ is an adjustment factor that controls the sensitivity of quantization adjustment; B(t) is the total available bandwidth of the system at time t; D... i (t) represents the amount of raw data i at time t. This formula ensures that when bandwidth is sufficient and data importance is high, the quantization level is low, thus maintaining high data accuracy; conversely, when bandwidth is limited or data importance is low, the quantization level is increased to reduce the amount of data and save bandwidth resources.

[0075] In one embodiment, the importance weight W of each crew monitoring data point i (t) is used to guide dynamic adjustments to bandwidth allocation, including weighting W based on the importance of each crew monitoring data point. i (t) Dynamically allocate bandwidth resources for each data stream.

[0076] This invention is based on a dynamic bandwidth allocation mechanism, according to the importance weight W of each monitoring data point. i (t) Allocate bandwidth for each data stream. The bandwidth allocation formula is designed as follows:

[0077]

[0078] Among them, B i (t) represents the bandwidth allocation for data i at time t, β is the bandwidth adjustment rate, which controls the smoothness of bandwidth changes, and Δt is the time step. This formula combines the current data importance ratio with historical bandwidth allocation, and achieves a smooth transition of bandwidth allocation through exponential decay, avoiding sudden bandwidth fluctuations and ensuring the stability and response speed of the communication system.

[0079] In one embodiment, to further refine bandwidth allocation, a minimum bandwidth requirement B can be introduced. min,i (t) and maximum bandwidth limit B max,i (t), defined as follows:

[0080]

[0081] Among them, B min,i(t) Ensure that each type of data receives at least the minimum bandwidth support, avoiding excessive concentration of resources on a few critical data points, which could leave other data with no bandwidth available; while B max,i (t) limits the bandwidth limit for each type of data to prevent a single data stream from consuming too much bandwidth resources and affecting the fairness of bandwidth allocation in the overall system.

[0082] In one embodiment, based on a determined quantization level Q i (t) The system partitions the data, with each partition corresponding to a send buffer. During this process, data with the same quantization level are assigned to the same buffer. This partitioning mechanism simplifies data management and provides a basis for subsequent targeted compression algorithm selection.

[0083] In one embodiment, based on the aforementioned importance weight W i (t) and adaptive quantization level Q i (t), quantifying various types of crew monitoring data. Quantification level Q i The determination of (t) is based on the importance of the data and the current system bandwidth, ensuring that critical data retains high accuracy when bandwidth is sufficient, while appropriately reducing accuracy to save bandwidth resources when bandwidth is limited. The quantized monitoring data is divided into different partitions according to its quantization level, and each partition corresponds to an independent transmission buffer.

[0084] Each transmit buffer is dedicated to storing data within the same quantization level range. This partitioning method allows the system to effectively manage data of varying precision and importance, improving the flexibility of data processing and transmission. Specifically, the quantization level partitioning can be set into multiple ranges; for example, a low quantization level corresponds to a high-precision data buffer, and a high quantization level corresponds to a low-precision data buffer. In this way, data compression strategies and transmission priorities in different buffers can be optimized specifically according to their quantization levels.

[0085] In one embodiment, the data in each transmit buffer is first subjected to corresponding compression processing. Since the data in the same buffer has similar quantization levels and data characteristics, using a uniform compression algorithm can more efficiently reduce the amount of data and improve compression efficiency. The compression algorithm can be a technique suitable for the quantized data characteristics, such as differential coding, decompression coding, or other efficient data compression methods, to minimize the amount of data transmitted and save bandwidth resources.

[0086] Once the data is correctly allocated to the corresponding transmit buffer, the system begins compressing the data within the buffer. Specifically, the data in each transmit buffer is compressed using an appropriate algorithm based on its quantization level. For high-precision data in the low-quantization-level buffer Buffer1, the system employs lossless compression algorithms such as ZIP or LZ77 to ensure that all detailed information of the data is completely preserved. These compression algorithms reduce the storage volume of the data without losing any original information and are suitable for critical monitoring data with extremely high requirements for data integrity.

[0087] Conversely, in high quantization level buffers k For low-precision data, the system employs lossy compression algorithms, such as Fourier transform-based compression methods. These algorithms further reduce the data volume by discarding some non-critical details, making them suitable for environmental monitoring data with relatively low precision requirements, thereby maximizing bandwidth savings.

[0088] In one embodiment, the data compression process is jointly performed by a hardware-level compression accelerator (such as a dedicated digital signal processor (DSP) or field-programmable gate array (FPGA)) and the processor of the data processing unit (DPU). The compression accelerator is responsible for efficiently executing the selected compression algorithm, significantly improving the data compression speed by utilizing its parallel processing capabilities, and ensuring that the compression process can be completed efficiently under real-time transmission requirements. The compression module software on the DPU dynamically selects and directs the compression accelerator to execute the corresponding compression task based on the quantization level of the transmit buffer. The compressed data is returned through a high-speed storage interface (such as DDR memory) and stored back in the corresponding transmit buffer, ready for subsequent data transmission.

[0089] In one embodiment, the bandwidth allocation mechanism is based on the importance weights w of various monitoring data points in each transmit buffer. i (t) and the corresponding bandwidth requirements are dynamically allocated. Specifically, the bandwidth B allocated to each send buffer... buffer,k (t). Calculated as the sum of bandwidth resources corresponding to all data within the buffer. This allocation formula ensures that each buffer receives appropriate transmission resources based on the importance and bandwidth requirements of the data within it, thereby optimizing the overall system's bandwidth utilization. The formula is as follows:

[0090]

[0091] Among them, buffer k B represents the data set in the k-th send buffer. i (t) represents the bandwidth resources required for data i at time t.

[0092] In one embodiment, the bandwidth allocation module software assigns a weighted average importance W to each crew monitoring data point. i (t) and the amount of data D in the send buffer j (t), dynamically calculate the bandwidth allocation B for each buffer. buffer,k (t).

[0093] After data compression is complete, the system enters the bandwidth allocation and priority transmission phase. The bandwidth allocation formula is as follows:

[0094]

[0095] in:

[0096] B buffer,k (t) represents the bandwidth allocation of the k-th send buffer at time t.

[0097] W i (t) represents the importance weight of each crew monitoring data point of data i at time t.

[0098] It is the sum of the importance weights of all crew monitoring data within buffer k.

[0099] B(t) represents the total available bandwidth of the system at time t.

[0100] β is the bandwidth adjustment rate, which controls the smoothness of bandwidth changes.

[0101] Δt is the time step.

[0102] B i (t-Δt) represents the bandwidth allocation of buffer k at the previous time step.

[0103] This invention combines the importance ratio of the current buffer. Compared with historical bandwidth allocation B i (t-Δt) utilizes an exponential decay mechanism to achieve a smooth transition in bandwidth allocation, avoiding sudden bandwidth fluctuations and ensuring the stability and response speed of the communication system.

[0104] In one embodiment, the crew monitoring data communication method of the present invention achieves efficient and real-time data transmission through close collaboration between hardware and software. First, sensors collect various types of crew monitoring data in real time. Preprocessing software on the DPU performs noise reduction and standardization on the data, and calculates the importance weight W of each type of crew monitoring data. i (t). Based on the weights and the current total bandwidth B(t), the quantization algorithm dynamically adjusts the quantization level Q of each data class. i (t), and then the quantized data is allocated to the corresponding send buffer.

[0105] Each transmit buffer selects an appropriate compression algorithm based on its quantization level. Hardware accelerators (DSP / FPGA) collaboratively process the compression task, and the compressed data is stored back into the buffer. The bandwidth management module manages the buffer's bandwidth requirements. biffer,k (t) Dynamically allocate total bandwidth and sort the buffers using transmission scheduling software.

[0106] During transmission, the system prioritizes transmitting data in buffers containing data types with high bandwidth allocation, ensuring efficient and timely transmission of critical data. The entire process is optimized for resource utilization and improved efficiency and reliability of the communication system through real-time monitoring and dynamic adjustments.

[0107] In one embodiment, during transmission, the system starts transmitting data from the buffer containing the monitoring data with the highest bandwidth allocated among the various monitoring data.

[0108] After bandwidth allocation is completed, the system sorts the transmission buffers according to the bandwidth allocation of the monitored data, and starts transmitting data from the buffer containing the monitored data with the highest bandwidth. Even if multiple buffers contain important data, the system will prioritize transmitting the transmission buffer containing the monitored data with the highest bandwidth allocation.

[0109] For example, if the buffer containing monitoring data 1, which has the highest allocated bandwidth, is buffer 1; the buffer containing monitoring data 2, which has the second highest allocated bandwidth, is buffer 2; the buffer containing monitoring data 3, which has the third highest allocated bandwidth, is buffer 1; and the buffer containing monitoring data 4, which has the fourth highest allocated bandwidth, is buffer 3, then the transmission priority within the buffers is buffer 1, followed by buffer 2, and finally buffer 3. However, the data corresponding to monitoring data 1 and monitoring data 3 in buffer 1 are transmitted together after quantization and compression, meaning that the transmission of monitoring data 3 will take precedence over monitoring data 2.

[0110] In practical implementation, the transmission scheduling module software runs on the DPU, sorting the transmission buffer in real time according to the bandwidth allocation results to generate a transmission queue for the buffer. Subsequently, the communication interface module extracts compressed data from the buffer sequentially according to the transmission queue and transmits it. The hardware-level communication interface module quickly reads the data from the transmission buffer through the Direct Memory Access (DMA) engine and sends the data to the central monitoring system through the physical layer interface.

[0111] In one embodiment, the system first transmits all data within the buffer containing the monitored data type with the highest bandwidth allocation. If bandwidth resources are still available, the system continues to transmit data in the next buffer in parallel, according to the buffer order. This process is controlled by the transmission scheduling module software, which directs the network switching equipment at the hardware layer to efficiently execute data transmission through the communication interface module, ensuring the priority transmission of critical data while making full use of remaining bandwidth to improve overall transmission efficiency.

[0112] Through this mechanism, the system can ensure that bandwidth resources are prioritized for the most critical data types, improve the real-time performance and reliability of data transmission, and maximize the amount of data transmission when bandwidth allows, thereby optimizing the overall performance of the communication system.

[0113] In one embodiment, the processor in the DPU is responsible for running software modules such as preprocessing, feature analysis, and quantization level adjustment, while a dedicated compression accelerator (DSP / FPGA) efficiently executes the selected compression algorithm. The transmit buffer consists of high-speed memory to ensure fast data read and write. The bandwidth management module and transmission scheduling module run at the software level of the DPU, working in conjunction with the network switching equipment at the hardware level through a communication interface to achieve dynamic optimization of bandwidth allocation and data transmission.

[0114] The software-level quantization and partitioning algorithms run on the DPU, monitoring the quantization level of the data in real time and allocating the data to the corresponding buffers. The compression module software, based on the quantization level of the transmit buffer, directs the compression accelerator to perform the corresponding compression task. The compressed data is returned via a high-speed interface and stored back in the transmit buffer, ready for transmission.

[0115] The bandwidth management module software assigns a weighted average of the importance of each crew monitoring data point to different data points. i (t) Calculate the bandwidth allocation B for each send buffer. buffer,k (t) and sends bandwidth allocation instructions to the network switching equipment through the communication interface. The network switching equipment adjusts the data transmission rate of each transmission buffer according to the received bandwidth allocation parameters to ensure the reasonable allocation and utilization of bandwidth resources.

[0116] In one embodiment, the sensor module collects crew monitoring data in real time and transmits it to the DPU via a data bus.

[0117] The preprocessing software on the DPU performs noise reduction and standardization on the acquired data, and stores the preprocessed data in a memory buffer.

[0118] The feature analysis software calculates the quantization level Q of the data on the DPU. i (t) and the importance weights of various crew monitoring data W i (t).

[0119] According to Q i (t) Allocate data to the corresponding send buffer. k .

[0120] The compression module selects a compression algorithm based on the quantization level of the transmit buffer, performs the compression task through a compression accelerator (DSP or FPGA), and stores the compressed data back to the corresponding transmit buffer.

[0121] The bandwidth management module calculates and allocates the bandwidth requirement B for each transmit buffer. buffer,k (t), and sends the bandwidth allocation command to the network switching device.

[0122] After sorting the transmission buffers according to the bandwidth allocation for each type of data, the transmission scheduling module determines the transmission queue of the transmission buffer area. The communication interface ensures that the data in the buffer containing the monitoring data type with high bandwidth allocation is sent first.

[0123] In one embodiment, the bandwidth management module determines the bandwidth requirement B of the buffer. buffer,k (t) Dynamically allocate total bandwidth and sort the buffers using transmission scheduling software.

[0124] During transmission, the system sorts the transmission buffers according to the bandwidth allocation of the monitored data. The system prioritizes transmitting data from the buffers at the front of the queue. If bandwidth resources are still available, the system continues to transmit data from the next buffer in parallel, according to the buffer sorting. In other words, the system sorts the buffers according to the transmission bandwidth corresponding to each data type and transmits data from each buffer sequentially according to resource availability.

[0125] This invention continuously monitors transmission status to ensure that as much data as possible is transmitted when bandwidth is available, while reducing the computational load for quantization in each buffer. The entire process optimizes resource utilization and improves the efficiency and reliability of the communication system through real-time monitoring and dynamic adjustments.

[0126] The communication method for crew monitoring data provided by this invention collects various types of crew monitoring data in real time and determines key indicator parameters based on data characteristics, such as data criticality, data change rate, anomaly probability, time sensitivity, and data dependency, to accurately calculate the importance weight of each monitoring data point. This weight guides the dynamic adjustment of quantification levels and bandwidth allocation, enabling the system to adaptively determine the optimal quantification level and bandwidth resource allocation strategy based on real-time data importance and current bandwidth conditions. By dynamically quantifying various types of monitoring data, this invention significantly improves the efficiency and reliability of data transmission, ensuring that critical data is prioritized for transmission even when network bandwidth is limited, thus reducing bandwidth waste. Simultaneously, the dynamic adjustment mechanism enhances the system's adaptability to changes in network conditions, improving the stability and response speed of the monitoring system in complex marine environments.

[0127] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0128] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0129] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0132] The preferred embodiments of the present invention have been described above to make the spirit of the present invention clearer and easier to understand, and are not intended to limit the present invention. All modifications, substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope summarized by the appended claims.

Claims

1. A communication method for monitoring crew monitoring data, the method comprising: Various types of crew monitoring data are collected in real time through sensors, and the index parameters of each monitoring data are determined based on the data characteristics. The importance weights of each crew monitoring data point are calculated, and these importance weights are used to guide the dynamic adjustment of the corresponding quantification level and bandwidth allocation. Based on the importance weight of each crew monitoring data and the current bandwidth availability, an adaptive quantization level is determined for each data point. Specifically, the higher the importance weight of the data and the more abundant the available bandwidth, the lower the quantization level is assigned to retain higher data accuracy; conversely, the lower the importance weight of the data or the more limited the available bandwidth, the higher the quantization level is assigned to reduce data accuracy. Based on the determined adaptive quantization level, various types of crew monitoring data are quantified. The quantization process refers to reducing the data representation precision according to the quantization level. The quantized monitoring data with the same or similar quantization levels are allocated to the same transmission buffer, and each transmission buffer corresponds to a quantization level range; Different data compression algorithms are used to process data in different transmit buffers according to their corresponding quantization level ranges; Bandwidth resources for each data stream are dynamically allocated based on the aforementioned importance weights; During transmission, the transmission priority of each transmission buffer is determined based on the sum of the importance weights of the data contained in each transmission buffer, and the data in each transmission buffer is transmitted in order of priority from high to low.

2. The communication method for crew monitoring data as described in claim 1, characterized in that, The indicator parameters include data criticality, data change rate, anomaly probability, time sensitivity, and data dependence.

3. The communication method for crew monitoring data as described in claim 1, characterized in that, Based on the determined quantification level of each monitoring data point, the system partitions the monitoring data, with each partition corresponding to a transmission buffer.

4. The communication method for crew monitoring data as described in claim 3, characterized in that, Monitoring data with the same quantization level are assigned to the same transmit buffer, and each transmit buffer is dedicated to storing data within the same quantization level range.

5. The communication method for crew monitoring data as described in claim 1, characterized in that, Multiple partitions are defined for transmitting buffers based on quantization levels, where low quantization levels correspond to high-precision transmitting buffers and high quantization levels correspond to low-precision transmitting buffers.

6. The communication method for crew monitoring data as described in claim 5, characterized in that, Perform appropriate compression processing on the data in each send buffer; The data compression algorithms used in the multiple send buffers are not exactly the same.

7. A communication method for crew monitoring data as described in claim 6, characterized in that, The data compression process is completed in collaboration between hardware-level compression acceleration and the processor of the data processing unit (DPU). Among them, the compression accelerator executes the selected compression algorithm and processes data compression in parallel. The compression module software on the DPU dynamically selects and directs the compression accelerator to execute the corresponding compression task according to the quantization level of the send buffer. The compressed data is returned via a high-speed storage interface and stored back in the corresponding send buffer.

8. The communication method for crew monitoring data as described in claim 1, characterized in that, The bandwidth allocated to each transmit buffer is calculated as the sum of the bandwidth resources allocated to all monitoring data within that transmit buffer.

9. A communication method for crew monitoring data as described in claim 1, characterized in that, During transmission, the system starts transmitting data from the buffer containing the monitoring data with the highest bandwidth allocated among all monitoring data. The system sorts the transmission buffers according to the bandwidth allocation of the monitored data, and generates a transmission queue for the buffer area; The communication interface module extracts compressed data from the buffer with the highest bandwidth allocation in sequence according to the transmission queue and transmits it. The hardware layer communication interface module reads data from the send buffer through the DMA engine and sends the data to the central monitoring system through the physical layer interface.

10. A communication system for monitoring crew data, the system comprising a memory and a processor, the memory storing a computer program, the processor executing the computer program stored in the memory to implement the method of any one of claims 1-9.

Images