Audio Distortion Adjustment Device and Method in Ship Communication Equipment

Abstract

The present invention discloses an audio distortion adjustment device and method in ship communication equipment, relating to the technical field of signal processing. The method includes: constructing a multi-dimensional environmental perception network to obtain the positioning, environment, and route information of the ship in real time, predicting the environmental trend, and generating an environmental change curve; based on the environmental change curve, dividing the environmental scene and extracting the extreme environment to generate multiple environmental prediction combinations, inputting the signal prediction model to predict the signal fluctuation, compensating for the signal distortion according to the signal fluctuation prediction sequence, and dynamically adjusting the audio signal during the execution through an adaptive signal compensation mechanism. The present invention solves the technical problem in the prior art that due to the diversity and complexity of the marine environment change, the real-time performance and stability of ship communication are poor, and achieves the technical effect of improving the real-time performance and stability of ship communication through real-time environmental trend prediction and dynamic compensation of audio signals.

Description

Technical Field

[0001] The present invention relates to the technical field of signal processing, and particularly to an audio distortion adjustment device and method in ship communication equipment. Background Art

[0002] In ship communication, the quality of audio signals directly affects communication efficiency and security. Especially in complex marine environments, ship audio signals are often interfered by various factors, such as signal attenuation, fluctuations, noise, etc., resulting in communication distortion. Existing ship communication equipment usually adopts signal compensation technology based on static models. However, the marine environment is complex and variable, and traditional audio distortion adjustment methods cannot respond to environmental changes and signal fluctuations in real time, resulting in unstable audio quality and affecting the real-time performance and stability of ship communication. Summary of the Invention

[0003] This application provides an audio distortion adjustment device and method in ship communication equipment, which is used to solve the technical problem that the real-time performance and stability of ship communication are poor due to the diversity and complexity of changes in the marine environment in the prior art.

[0004] In the first aspect of this application, an audio distortion adjustment method in ship communication equipment is provided. The method includes: constructing a multi-dimensional environment perception network, obtaining the real-time positioning information, real-time environment information, and target route information of the target ship, performing environmental trend prediction, and generating an environmental change curve; based on the environmental change curve, performing environmental scenario division and extreme environment extraction to generate multiple environmental prediction combinations; inputting the multiple environmental prediction combinations into a signal prediction model, matching the corresponding signal fluctuation prediction unit, performing signal fluctuation prediction, and obtaining a signal fluctuation prediction sequence; performing signal distortion compensation according to the signal fluctuation prediction sequence to generate an initial compensation scheme, and during the execution of the initial compensation scheme, performing dynamic adjustment of the audio signal through an adaptive signal compensation mechanism.

[0005] In the second aspect of the present application, an audio distortion adjustment device in a ship communication device is provided. The device includes: an environmental trend prediction module, which is used to construct a multi-dimensional environmental perception network, obtain real-time positioning information, real-time environmental information, and target route information of a target ship, perform environmental trend prediction, and generate an environmental change curve; an environmental scenario extraction module, which is used to perform environmental scenario division and extreme environment extraction based on the environmental change curve, and generate multiple environmental prediction combinations; a signal fluctuation prediction module, which is used to input the multiple environmental prediction combinations into a signal prediction model, match corresponding signal fluctuation prediction units, perform signal fluctuation prediction, and obtain a signal fluctuation prediction sequence; an audio signal adjustment module, which is used to perform signal distortion compensation according to the signal fluctuation prediction sequence, generate an initial compensation scheme, and perform dynamic adjustment of the audio signal through an adaptive signal compensation mechanism during the execution of the initial compensation scheme.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0007] The audio distortion adjustment device and method in a ship communication device provided in the present application relate to the technical field of signal processing. By constructing a multi-dimensional environmental perception network, real-time acquisition of ship positioning, environment, and route information is carried out, environmental trend prediction and environmental scenario division are performed, multiple environmental prediction combinations are generated, and input into a signal prediction model for signal fluctuation prediction. Signal distortion compensation is performed according to the prediction sequence, and the audio signal is dynamically adjusted through an adaptive mechanism. It solves the technical problem in the prior art that due to the diversity and complexity of the marine environment change, the real-time performance and stability of ship communication are poor, and realizes the technical effect of improving the real-time performance and stability of ship communication through real-time environmental trend prediction and dynamic compensation of audio signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 It is a schematic flowchart of the audio distortion adjustment method in the ship communication device provided in the embodiment of the present application;

[0010] Figure 2 It is a schematic structural diagram of the audio distortion adjustment device in the ship communication device provided in the embodiment of the present application.

[0011] Description of the accompanying drawing reference numerals: environmental trend prediction module 11, environmental scenario extraction module 12, signal fluctuation prediction module 13, audio signal adjustment module 14. Specific implementation mode

[0012] The present application provides an audio distortion adjustment device and method in a ship communication device, which is used to solve the technical problem that the real-time performance and stability of ship communication are poor due to the diversity and complexity of the marine environment change in the prior art.

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative work shall fall within the protection scope of the present application.

[0014] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above accompanying drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0015] Embodiment 1, as Figure 1 shown, the present application provides an audio distortion adjustment method in a ship communication device, and the method includes:

[0016] P10: Construct a multi-dimensional environmental perception network, obtain the real-time positioning information, real-time environmental information and target route information of the target ship, perform environmental trend prediction, and generate an environmental change curve.

[0017] Further, step P10 of the embodiment of the present application further includes:

[0018] P11: Construct a multi-dimensional environmental perception network. The multi-dimensional environmental perception network includes a multi-sensor module and an environmental trend prediction model. Moreover, the multi-dimensional environmental perception network executes a dynamic progressive prediction mechanism; P12: Based on the multi-sensor module, perform multi-source data collection to obtain the real-time positioning information, real-time environmental information, and target route information of the target ship; P13: Input the real-time positioning information, real-time environmental information, and target route information into the environmental trend prediction model for environmental trend prediction to generate an environmental change curve; P14: According to the dynamic progressive prediction mechanism, perform rolling environmental data collection and environmental change prediction at preset intervals to dynamically correct the environmental change curve.

[0019] It should be understood that by constructing a multi-dimensional environmental perception network, comprehensive monitoring and dynamic prediction of the environment where the target ship is located are achieved, providing an accurate environmental basis for audio distortion adjustment.

[0020] First, construct a multi-dimensional environmental perception network, which consists of a multi-sensor module and an environmental trend prediction model. Among them, the multi-sensor module is responsible for collecting different types of environmental data, such as the real-time positioning of the ship, environmental meteorological parameters (wind speed, temperature, air pressure, etc.), and route information. The environmental trend prediction model processes these data to generate prediction information on environmental changes. This network executes a dynamic progressive prediction mechanism, that is, continuously updates and predicts the changing trend of the environment according to the real-time collected data, ensuring a high degree of consistency between the prediction results and the actual environmental state.

[0021] Specifically, through the multi-sensor module, multi-dimensional data collection is carried out. These data include the real-time positioning information of the target ship (such as longitude and latitude, speed, heading, etc.), real-time environmental information (such as meteorological conditions, ocean conditions, etc.), and target route information (including voyage, estimated arrival time, etc.). The role of the multi-sensor module is to collect data in multiple dimensions, provide comprehensive information, and lay a foundation for environmental trend prediction.

[0022] Input the collected real-time positioning information, environmental information, and route data into the environmental trend prediction model. The environmental trend prediction model is based on machine learning and data analysis algorithms, and can identify the patterns of environmental changes and perform trend prediction. The prediction results are presented in the form of environmental change curves, intuitively showing the changing trend of the environment in a future period of time. These change curves can reflect meteorological conditions, ocean dynamics, and other environmental factors that may affect ship communication, thus providing key information for subsequent audio distortion adjustment.

[0023] Adopt a dynamic progressive prediction mechanism. Every predetermined period (such as every minute, every hour, etc.), re-collect environmental data and predict environmental changes. This rolling update mechanism ensures the high sensitivity of the system to environmental changes and can dynamically correct the environmental change curve. Through dynamic correction, the model can reflect the minute changes in the environment in real time, making the prediction results more in line with the actual situation, thereby improving the compensation accuracy. The dynamic progressive prediction mechanism not only improves the real-time performance of prediction but also can quickly respond to sudden environmental changes, providing more reliable real-time data support, enabling the system to continuously self-adjust, enhancing the response ability to emergencies, and further improving the stability and reliability of ship communication equipment in a dynamic environment.

[0024] P20: Based on the environmental change curve, conduct environmental scenario division and extreme environment extraction to generate multiple environmental prediction combinations.

[0025] Furthermore, step P20 of the embodiment of the present application further includes:

[0026] P21: Conduct trend analysis on the environmental change curve to identify and obtain multiple environmental feature sets; P22: Conduct cluster analysis on the multiple environmental feature sets to divide multiple weather scenarios; P23: Based on the environmental change curve, extract extreme environmental nodes exceeding the environmental threshold and mark them as extreme scenarios; P24: Combine the multiple weather scenarios and extreme environmental nodes to generate multiple environmental prediction combinations, and the multiple environmental prediction combinations cover normal and extreme environmental conditions.

[0027] Optionally, based on the generated environmental change curve, conduct in-depth analysis and division of environmental data, identify different environmental scenarios, and extract extreme environmental conditions to provide a basis for generating more accurate and comprehensive prediction combinations.

[0028] First, conduct trend analysis on the generated environmental change curve. Through trend analysis algorithms (such as regression analysis or moving average method), the regular changes in the curve can be extracted. These changes include information such as short-term fluctuations and long-term trends of the climate, and multiple environmental feature sets are identified from them. These environmental feature sets represent the change patterns of environmental variables (such as temperature, humidity, wind speed, etc.) at different time periods. For example, a rapid increase in temperature within a certain period may represent the approaching of high-temperature weather, while an increase in wind speed may indicate the coming of a storm.

[0029] Next, perform clustering analysis on the identified multiple sets of environmental features. Use clustering algorithms (such as K-means clustering or hierarchical clustering) to divide the environmental features into multiple weather scenarios according to their similarity. These scenarios can include regular weather conditions (such as sunny, shower, etc.) and abnormal weather conditions (such as strong wind, thunderstorm, etc.). Through clustering analysis, the system can automatically group different environmental patterns for subsequent environmental combination generation and prediction.

[0030] After analyzing the environmental change curve, the system will further extract extreme environmental nodes that exceed the preset environmental threshold. These nodes represent extreme weather conditions that may have a significant impact on ship communication, such as extremely high temperature, high wind speed, lightning, etc. By setting the environmental threshold, these extreme environmental nodes can be automatically identified and marked, and classified as extreme scenarios. Extreme scenarios usually require special treatment because they may have a non-negligible impact on the performance, stability, and signal quality of communication equipment.

[0031] Finally, combine the divided multiple weather scenarios with the marked extreme environmental nodes to generate multiple environmental prediction combinations. These combinations cover not only regular weather changes (such as sunny day, shower, etc.), but also extreme weather scenarios (such as typhoon, heavy snow, etc.). Through such environmental combinations, the system can comprehensively predict the communication signal performance under different environmental conditions, and provide a multi-dimensional basis for subsequent signal fluctuation prediction and distortion compensation. Generating multiple environmental prediction combinations by combining regular and extreme environmental scenarios can ensure that the communication system can adapt to various complex and changeable environmental conditions, thereby enhancing the robustness and flexibility of the system.

[0032] P30: Input the multiple environmental prediction combinations into the signal prediction model, match the corresponding signal fluctuation prediction unit, perform signal fluctuation prediction, and obtain a signal fluctuation prediction sequence.

[0033] It should be understood that according to multiple environmental prediction combinations, the signal fluctuation is predicted through the signal prediction model, and then the predicted signal fluctuation sequence is obtained, providing a basis for subsequent signal distortion compensation. The core of this process is to use historical data and environmental change prediction, combined with machine learning or deep learning models, to model and predict the impact of environmental changes on signal fluctuations.

[0034] Specifically, first, take the multiple environmental prediction combinations as input data and input them into the signal prediction model. These environmental prediction combinations contain various environmental scenarios, including regular and extreme weather conditions, such as sunny day, shower, strong wind, thunderstorm, etc. The signal prediction model can identify the signal fluctuation patterns under each environmental condition according to different environmental changes. The input data usually includes environmental feature sets (such as temperature, humidity, wind speed, etc.) and the corresponding environmental scenarios (such as strong wind, thunderstorm, etc.), and these data constitute the multi-dimensional information input to the model.

[0035] In the signal prediction model, according to the input environmental prediction combination, the system will automatically match the corresponding signal fluctuation prediction unit. Each prediction unit is responsible for modeling the signal fluctuation in a specific environmental scenario, usually using time series prediction methods (such as ARIMA model, long short-term memory network LSTM, etc.) for modeling. Different signal fluctuation prediction units generate corresponding signal fluctuation prediction models based on different environmental characteristics and historical data. For example, in strong wind weather, the signal may be more interfered with, so the fluctuation amplitude is larger, while in stable weather conditions, the signal fluctuation is smaller. By matching specific environmental scenarios and corresponding fluctuation prediction units, the system can more accurately simulate the change trend of the signal under different environmental conditions.

[0036] After completing the prediction unit matching, the signal prediction model will perform signal fluctuation prediction according to the selected prediction unit. The model will use regression analysis, deep neural network or other machine learning algorithms to predict the trend of signal fluctuation in the future time period based on historical data and the input environmental prediction combination. Through the time series analysis of signal fluctuation, the signal strength change situation at multiple time points and the possible fluctuation amplitude can be obtained. For example, the model may predict that within the next 10 minutes, the signal will have 2 obvious fluctuations, and the amplitude of each fluctuation is 10%. These prediction information provides a real-time basis for subsequent signal compensation.

[0037] Finally, the signal prediction model will output a complete signal fluctuation prediction sequence, which represents the expected change of signal strength in the future period of time. The signal fluctuation prediction sequence not only contains the time nodes of signal change, but also contains the predicted values and fluctuation amplitudes at each time node. This information can help the communication system identify and process signal changes in advance, and provide accurate reference data for subsequent signal distortion compensation.

[0038] Through the above steps, it is possible to quickly predict the signal fluctuation sequence according to the real-time environmental changes, and provide high-precision data support for signal distortion compensation. This process will improve the signal reliability and stability of ship communication equipment under complex environmental conditions, and effectively avoid communication failures caused by signal fluctuations.

[0039] P40: Perform signal distortion compensation according to the signal fluctuation prediction sequence, generate an initial compensation scheme, and during the execution of the initial compensation scheme, perform dynamic adjustment of the audio signal through an adaptive signal compensation mechanism.

[0040] Furthermore, step P40 of the embodiment of the present application further includes:

[0041] P41: Extract key fluctuation features according to the signal fluctuation prediction sequence, and determine the signal distortion type based on the key fluctuation features, where the signal distortion type includes at least one type; P42: Based on the signal distortion type, match the target signal compensation calculation unit, and generate a corresponding signal compensation scheme in combination with the predicted signal distortion information; P43: Generate the initial compensation scheme by integrating various types of predicted signal distortion information and signal compensation schemes.

[0042] In a possible embodiment of the present application, signal distortion that may occur is compensated according to the signal fluctuation prediction sequence, and an initial compensation scheme is generated. To ensure the accuracy and real-time performance of the compensation process, in this step, the key features in the signal fluctuation are extracted, the signal distortion type is identified, and the compensation strategy for the audio signal is dynamically generated and adjusted according to the prediction result.

[0043] First, extract the key fluctuation features according to the signal fluctuation prediction sequence. These key features usually include the amplitude fluctuation, frequency change, and phase shift of the signal, etc. Through the feature analysis of the signal fluctuation, it is possible to identify which fluctuations are caused by environmental factors and which fluctuations belong to the abnormal or distorted parts. Common signal distortion types include amplitude distortion, frequency distortion, phase distortion, etc. Specifically, amplitude distortion usually manifests as a sudden increase or decrease in the signal intensity, and frequency distortion manifests as a shift in the signal frequency, and this kind of distortion may affect the communication quality and cause signal reception errors.

[0044] By analyzing the features in the signal fluctuation prediction sequence, the type of signal distortion can be clearly determined. For example, in bad weather conditions, strong winds may cause amplitude distortion of the signal, while thunderstorm weather may cause frequency distortion of the signal. The determination of this distortion type is the basis for formulating the subsequent compensation scheme.

[0045] Next, automatically select a suitable signal compensation calculation unit according to the identified signal distortion type. For example, in the case of amplitude distortion, a gain control algorithm may need to be applied to restore the signal intensity; while in the case of frequency distortion, a frequency correction algorithm may need to be used to correct the frequency shift of the signal. The signal compensation calculation unit can be based on traditional digital signal processing (DSP) technology or optimized by combining modern machine learning methods. This unit will generate a preliminary signal compensation scheme in combination with the predicted signal distortion information, ensuring that the compensation strategy is adjusted according to the specific distortion type and distortion amplitude. Moreover, the generation of the compensation scheme not only depends on the signal distortion type but also needs to consider the influence of other environmental factors (such as ship movement, weather changes, etc.) on the signal. Therefore, the system needs to continuously receive real-time data and dynamically adjust the compensation strategy to cope with signal fluctuations in different scenarios.

[0046] After the initial compensation scheme is generated, it will combine different types of signal distortion information and integrate all the generated compensation strategies to form an initial compensation scheme. This scheme is the basic one for correcting signal distortion and usually includes the adjustment of signal amplitude, the repair of frequency offset, and the suppression of noise, etc. To ensure the optimization of the compensation effect, the system will dynamically adjust the execution process of the compensation scheme. Through the adaptive signal compensation mechanism, it monitors the compensation effect in real time and automatically adjusts the compensation strategy according to the actual signal quality feedback. For example, if the signal distortion is not fully compensated, the system will increase the amplitude of signal enhancement or adjust the accuracy of frequency compensation. The adaptive mechanism ensures that in complex environmental conditions, the compensation process can flexibly respond to changes in signal quality.

[0047] Through the above steps, this application can quickly generate a targeted signal compensation scheme based on real-time signal fluctuation prediction and the identification of signal distortion types, and ensure the optimization of the compensation effect through dynamic adjustment. This process significantly improves the signal stability of ship communication equipment in complex environments, effectively reduces communication interference caused by signal distortion, and ensures the improvement of communication quality.

[0048] Furthermore, the embodiment of this application further includes step P50, and step P50 further includes:

[0049] P51: Connect to the distributed computing platform and split the calculation tasks of signal fluctuation prediction and signal distortion compensation into multiple parallel subtasks respectively; P52: Process the multiple parallel subtasks in parallel to quickly generate a signal compensation scheme.

[0050] Optionally, in this embodiment, to meet the requirements of real-time and high efficiency in ship communication, a distributed computing platform is adopted to accelerate the calculation process of signal fluctuation prediction and distortion compensation. The distributed computing platform realizes the rapid processing of calculation tasks by splitting the signal prediction and compensation tasks into multiple parallel subtasks, and greatly reduces the calculation time and delay, ensuring timely response to environmental changes and signal distortion.

[0051] First, by connecting to the distributed computing platform, the entire calculation process of signal fluctuation prediction and distortion compensation is split into multiple parallel subtasks. The distributed computing platform is usually based on a cloud computing architecture or a high-performance computing cluster, and it can process a large amount of data and perform distributed computing. In this process, the signal fluctuation prediction and distortion compensation tasks are decomposed into independent modules, and each module is responsible for different calculation tasks. For example:

[0052] For signal fluctuation prediction, the fluctuation prediction process can be divided into signal fluctuation calculation tasks for multiple regions, with each subtask responsible for processing signal predictions under different ship positions and different environmental conditions. For signal distortion compensation, the compensation tasks can be split into multiple subtasks according to the distortion type and compensation strategy, and each subtask performs compensation calculations for a specific type of distortion (such as frequency distortion, amplitude distortion, etc.). This way of task splitting can improve the parallel computing efficiency and accelerate the entire signal processing flow.

[0053] After splitting the tasks, the distributed computing platform will execute these parallel subtasks simultaneously. Each subtask runs independently, utilizes the resources of the computing platform to process data in parallel, and completes its own computing task. Through parallel processing, the system can obtain the computing results of each subtask in a relatively short time, thereby quickly generating a signal compensation scheme.

[0054] The key advantage of parallel computing is that it significantly reduces the total computing duration. For example, in traditional serial computing, all tasks must be executed sequentially in order, while parallel computing enables multiple tasks to be carried out simultaneously by allocating computing resources, greatly shortening the time. The resource scheduling and task allocation mechanism of the distributed platform ensure the efficiency and stability of the computing process.

[0055] By parallelly splitting the signal fluctuation prediction and distortion compensation tasks, the efficiency of the computing process is achieved. Traditional signal processing methods usually adopt serial computing methods, which are prone to delays, while this solution greatly accelerates the processing speed through parallel computing, ensuring that the compensation scheme can be adjusted in real time in a dynamic environment, and improving the response speed and stability of ship communication.

[0056] In addition, the introduction of the distributed computing platform makes the system have better scalability, capable of handling more complex and dynamic environmental data and communication tasks, ensuring that accurate signal compensation schemes can still be quickly generated under different environmental changes and large-scale data streams.

[0057] Furthermore, step P51 of the embodiment of the present application further includes:

[0058] P51-1: Adopt a distributed computing architecture to build a distributed computing platform, and the distributed computing platform is configured with multiple independent computing nodes and corresponding storage spaces; P51-2: Based on the distributed computing platform, divide the signal fluctuation prediction tasks according to time windows or geographical regions to generate multiple fluctuation prediction subtasks, and divide the distortion compensation tasks according to the signal distortion type to obtain multiple distortion compensation subtasks; P51-3: Correlate and correspond the multiple fluctuation prediction subtasks and the multiple distortion compensation subtasks to generate the multiple parallel subtasks.

[0059] It should be understood that through a more precise configuration of the distributed computing architecture, the parallel processing process of signal fluctuation prediction and signal distortion compensation is further optimized.

[0060] First, a computing platform is built by adopting a distributed computing architecture. The platform consists of multiple independent computing nodes, and each node is configured with an independent storage space and can independently process computing tasks. Each computing node has a certain computing power and storage capacity, can independently process the tasks assigned to it, and can also cooperate with other nodes to jointly complete large-scale computing tasks.

[0061] The design of this distributed architecture can ensure that the platform has high scalability and can dynamically expand computing resources according to the task load. For example, when the computing requirements for signal prediction and compensation increase, the system can automatically add new computing nodes to cope with higher computing requirements. At the same time, the independent storage spaces of each node ensure the distributed storage and fast access of data, avoiding the problem of single-node storage bottlenecks.

[0062] After building the distributed computing platform, the system divides the computing tasks according to specific requirements. For the signal fluctuation prediction task, the fluctuation prediction task can be divided into multiple subtasks according to the time window (such as prediction in hours) or geographical area (such as the locations of different ships). This can localize the prediction task so that each computing node can independently execute the signal fluctuation calculations in different regions or time periods, thereby improving the computing efficiency.

[0063] For the signal distortion compensation task, the task can be divided according to different signal distortion types (such as amplitude distortion, frequency distortion, etc.). Each subtask is responsible for a specific type of distortion compensation to ensure that the most suitable compensation strategy is adopted for different distortion problems. Through this division method, the computing resources can be maximally utilized to achieve parallel processing of tasks.

[0064] After completing the task division, the system will reasonably associate multiple signal fluctuation prediction subtasks and distortion compensation subtasks according to the relevance between tasks. This step identifies which signal fluctuation prediction tasks and distortion compensation tasks are related in time or space and combines them into parallel subtasks so that related computing tasks can be executed at the same time. For example, when the signal fluctuation prediction in a certain area is completed, the related distortion compensation task can be immediately started to avoid delays caused by the sequential relationship between tasks. Through task association, various types of data can be processed more efficiently, and the generation of the compensation scheme can be made more compact and timely.

[0065] By precisely dividing the signal fluctuation prediction task and the distortion compensation task, and leveraging the parallel processing capabilities of the distributed computing platform, this embodiment can effectively improve the computing efficiency, reduce the processing delay, and meet the strict requirements of the ship communication system for real-time performance and high efficiency. The distributed computing architecture not only ensures the scalability of the platform but also provides technical support for the efficient processing of complex computing tasks.

[0066] Further, step P52 of the embodiment of the present application further includes:

[0067] P52-1: Perform priority sorting on the multiple parallel subtasks, and according to the priority sorting result, extract the high-priority subtasks, perform splitting granularity optimization, and generate a priority processing task subset; P52-2: Use the priority processing task subset to update and replace the multiple parallel subtasks to generate a refined parallel subtask set; P52-3: According to the multiple independent computing nodes and the corresponding storage spaces, through a load balancing mechanism, evenly distribute the refined parallel subtask set to form multiple task processing units; P52-4: Perform parallel signal distortion compensation analysis with the multiple task processing units to generate a signal compensation scheme.

[0068] Specifically, refine the multiple parallel subtasks to ensure that the tasks can be executed efficiently, preferentially, and evenly.

[0069] First, perform priority sorting on the divided multiple parallel subtasks. The priority sorting is determined based on the importance, urgency of the tasks, and the impact on the final signal compensation effect. For example, the signal fluctuation prediction subtasks may need to be sorted according to the urgency of the actual environmental changes, while the distortion compensation subtasks need to be prioritized according to the severity of the distortion type.

[0070] After sorting, the system extracts the high-priority subtasks and performs splitting granularity optimization on these high-priority tasks. The purpose of granularity optimization is to reduce the management burden brought by excessive small-granularity tasks while ensuring the accuracy of the tasks. By adjusting the task granularity, the optimal utilization of computing resources can be achieved, avoiding over-splitting or overly rough task division, and improving the system processing efficiency. Finally, these optimized high-priority tasks will form a priority processing task subset for subsequent further processing.

[0071] After generating the subset of prioritized tasks, the system will update and replace the original parallel subtasks. This update and replacement is not just a simple task replacement, but rather an adjustment of the task execution order and processing strategy based on the task priority, optimized granularity, and real-time changes in the execution environment. By this method, it can be ensured that during the task execution process, high-priority tasks are processed first, while low-priority tasks can be postponed or processed in parallel when resources permit. This process will generate a refined set of parallel subtasks, that is, a set of parallel tasks that have been optimized and adjusted, and these tasks can match the computing resources more efficiently and minimize the system's processing bottlenecks.

[0072] After generating the refined set of parallel subtasks, the system will evenly distribute the task set to multiple independent computing nodes through a load balancing mechanism. The load balancing mechanism aims to ensure that the load of each computing node remains within a reasonable range, avoiding overloading of a single node or waste of idle resources. By evenly distributing tasks, the computing resources of the system can be utilized most effectively, avoiding task backlogs or resource waste. After the tasks of each computing node are assigned, multiple task processing units are formed, and each unit independently executes the computing tasks it is responsible for to ensure the efficient parallel processing of tasks.

[0073] Finally, after the task processing units are formed, the system will start these parallel processing units to analyze the signal distortion and perform specific parallel signal distortion compensation analysis. Through parallel processing, multiple task processing units simultaneously analyze different signal fluctuation characteristics, distortion types, and environmental conditions, and quickly generate a signal compensation scheme. This parallel analysis greatly improves the response speed of signal distortion compensation, enabling the ship communication equipment to perform real-time and accurate distortion compensation for signals.

[0074] In summary, the embodiments of the present application have at least the following technical effects:

[0075] The present application constructs a multi-dimensional environment perception network to obtain the positioning, environment, and route information of the ship in real time, predict the environmental trend, generate an environmental change curve, based on the environmental change curve, perform environmental scenario division and extreme environment extraction, generate multiple environmental prediction combinations, input the signal prediction model for signal fluctuation prediction, perform signal distortion compensation according to the signal fluctuation prediction sequence, and through an adaptive signal compensation mechanism, perform dynamic adjustment of the audio signal during the execution process.

[0076] It achieves the technical effect of improving the real-time performance and stability of ship communication through real-time environmental trend prediction and dynamic compensation of audio signals.

[0077] Embodiment 2, based on the same inventive concept as the audio distortion adjustment method in the ship communication equipment in the foregoing embodiment, such as Figure 2As shown, the present application provides an audio distortion adjustment device in a ship communication device. The device and method embodiments in the embodiments of the present application are based on the same inventive concept. Among them, the device includes:

[0078] An environmental trend prediction module 11, which is used to construct a multi-dimensional environmental perception network, obtain the real-time positioning information, real-time environmental information, and target route information of the target ship, perform environmental trend prediction, and generate an environmental change curve.

[0079] An environmental scenario extraction module 12, which is used to perform environmental scenario division and extreme environment extraction based on the environmental change curve, and generate multiple environmental prediction combinations.

[0080] A signal fluctuation prediction module 13, which is used to input the multiple environmental prediction combinations into a signal prediction model, match the corresponding signal fluctuation prediction unit, perform signal fluctuation prediction, and obtain a signal fluctuation prediction sequence.

[0081] An audio signal adjustment module 14, which is used to perform signal distortion compensation according to the signal fluctuation prediction sequence, generate an initial compensation scheme, and perform dynamic adjustment of the audio signal through an adaptive signal compensation mechanism during the execution of the initial compensation scheme.

[0082] Furthermore, the environmental trend prediction module 11 is further used to perform the following steps:

[0083] Construct a multi-dimensional environmental perception network, which includes a multi-sensor module and an environmental trend prediction model, and the multi-dimensional environmental perception network executes a dynamic progressive prediction mechanism; based on the multi-sensor module, perform multi-source data collection to obtain the real-time positioning information, real-time environmental information, and target route information of the target ship; input the real-time positioning information, real-time environmental information, and target route information into the environmental trend prediction model for environmental trend prediction, and generate an environmental change curve; according to the dynamic progressive prediction mechanism, perform rolling environmental data collection and environmental change prediction at a preset period, and dynamically correct the environmental change curve.

[0084] Furthermore, the environmental scenario extraction module 12 is further used to perform the following steps:

[0085] Perform trend analysis on the environmental change curve to identify and obtain multiple environmental feature sets; perform clustering analysis on the multiple environmental feature sets to divide multiple weather scenarios; based on the environmental change curve, extract extreme environmental nodes exceeding the environmental threshold and label them as extreme scenarios; combine the multiple weather scenarios and extreme environmental nodes to generate multiple environmental prediction combinations, which cover both normal and extreme environmental conditions.

[0086] Further, the audio signal adjustment module 14 is further configured to perform the following steps:

[0087] Extract key fluctuation features according to the signal fluctuation prediction sequence, and determine the signal distortion type according to the key fluctuation features, where the signal distortion type includes at least one; based on the signal distortion type, match the target signal compensation calculation unit, and generate a corresponding signal compensation scheme in combination with the predicted signal distortion information; integrate various types of predicted signal distortion information and signal compensation schemes to generate the initial compensation scheme.

[0088] Further, the device further includes:

[0089] A computing task splitting module, which is used to connect to a distributed computing platform and split the computing tasks of signal fluctuation prediction and signal distortion compensation into multiple parallel subtasks respectively; a parallel processing module, which is used to perform parallel processing on the multiple parallel subtasks to quickly generate a signal compensation scheme.

[0090] Further, the computing task splitting module is further configured to perform the following steps:

[0091] Adopt a distributed computing architecture to build a distributed computing platform, which is configured with multiple independent computing nodes and corresponding storage spaces; based on the distributed computing platform, divide the signal fluctuation prediction task according to the time window or geographical area to generate multiple fluctuation prediction subtasks, and divide the distortion compensation task according to the signal distortion type to obtain multiple distortion compensation subtasks; associate and correspond the multiple fluctuation prediction subtasks and the multiple distortion compensation subtasks to generate the multiple parallel subtasks.

[0092] Further, the parallel processing module is further configured to perform the following steps:

[0093] Prioritize the multiple parallel subtasks, and according to the prioritization result, extract the high-priority subtasks, optimize the splitting granularity, and generate a subset of tasks to be processed first; use the subset of tasks to be processed first to update and replace the multiple parallel subtasks to generate a refined parallel subtask set; according to the multiple independent computing nodes and the corresponding storage spaces, through a load balancing mechanism, evenly distribute the refined parallel subtask set to form multiple task processing units; perform parallel signal distortion compensation analysis with the multiple task processing units to generate a signal compensation scheme.

[0094] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0095] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0096] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. Method for adjusting audio distortion in ship communication equipment, characterized in that, The method includes: Constructing a multi-dimensional environmental perception network, obtaining real-time positioning information, real-time environmental information, and target route information of a target ship, predicting environmental trends, and generating an environmental change curve; Based on the environmental change curve, performing environmental scenario division and extreme environment extraction to generate multiple environmental prediction combinations; Inputting the multiple environmental prediction combinations into a signal prediction model, matching corresponding signal fluctuation prediction units, performing signal fluctuation prediction, and obtaining a signal fluctuation prediction sequence; Performing signal distortion compensation according to the signal fluctuation prediction sequence to generate an initial compensation scheme, and dynamically adjusting the audio signal through an adaptive signal compensation mechanism during the execution of the initial compensation scheme; Among them, constructing a multi-dimensional environmental perception network, obtaining real-time positioning information, real-time environmental information, and target route information of a target ship, predicting environmental trends, and generating an environmental change curve includes: Constructing a multi-dimensional environmental perception network, the multi-dimensional environmental perception network includes a multi-sensor module and an environmental trend prediction model, and the multi-dimensional environmental perception network executes a dynamic progressive prediction mechanism; Based on the multi-sensor module, performing multi-source data collection to obtain real-time positioning information, real-time environmental information, and target route information of the target ship; Inputting the real-time positioning information, real-time environmental information, and target route information into the environmental trend prediction model for environmental trend prediction to generate an environmental change curve; Based on the environmental change curve, performing environmental scenario division and extreme environment extraction to generate multiple environmental prediction combinations includes: Performing trend analysis on the environmental change curve to identify and obtain multiple environmental feature sets; Performing clustering analysis on the multiple environmental feature sets to divide multiple weather scenarios; Based on the environmental change curve, extracting extreme environmental nodes exceeding the environmental threshold and marking them as extreme scenarios; Combining the multiple weather scenarios and extreme environmental nodes to generate multiple environmental prediction combinations, and the multiple environmental prediction combinations cover conventional and extreme environmental conditions.

2. The method for adjusting audio distortion in the ship communication device according to claim 1, characterized in that, The method further includes: Connecting to a distributed computing platform, and separately splitting the computing tasks of signal fluctuation prediction and signal distortion compensation into multiple parallel subtasks; Performing parallel processing on the multiple parallel subtasks to quickly generate a signal compensation scheme.

3. The method for adjusting audio distortion in the ship communication device according to claim 2, wherein Connecting to a distributed computing platform, and separately splitting the computing tasks of signal fluctuation prediction and signal distortion compensation into multiple parallel subtasks includes: Adopting a distributed computing architecture to build a distributed computing platform, and the distributed computing platform is configured with multiple independent computing nodes and corresponding storage spaces; Based on the distributed computing platform, dividing the signal fluctuation prediction task according to a time window or geographical area to generate multiple fluctuation prediction subtasks, and dividing the distortion compensation task according to the signal distortion type to obtain multiple distortion compensation subtasks; Associating and corresponding the multiple fluctuation prediction subtasks and the multiple distortion compensation subtasks to generate the multiple parallel subtasks.

4. The method for adjusting audio distortion in the ship communication device according to claim 3, wherein Performing parallel processing on the multiple parallel subtasks to quickly generate a signal compensation scheme includes: Rank the priorities of the multiple parallel subtasks, and according to the priority ranking result, extract the high-priority subtasks, optimize the splitting granularity, and generate a subset of tasks to be processed first; Use the subset of tasks to be processed first to update and replace the multiple parallel subtasks, and generate a refined set of parallel subtasks; According to the multiple independent computing nodes and the corresponding storage spaces, through a load balancing mechanism, evenly distribute the refined set of parallel subtasks to form multiple task processing units; Perform parallel signal distortion compensation analysis with the multiple task processing units to generate a signal compensation scheme.

5. The method for adjusting audio distortion in the ship communication device according to claim 1, characterized in that Construct a multi-dimensional environment perception network, obtain the real-time positioning information, real-time environment information, and target route information of the target ship, perform environment trend prediction, and generate an environmental change curve. It also includes: According to the dynamic progressive prediction mechanism, perform rolling environmental data collection and environmental change prediction at a preset cycle, and dynamically correct the environmental change curve.

6. The method for adjusting audio distortion in the ship communication device according to claim 1, characterized in that, Perform signal distortion compensation according to the signal fluctuation prediction sequence to generate an initial compensation scheme, including: According to the signal fluctuation prediction sequence, extract key fluctuation features, and determine the signal distortion type according to the key fluctuation features. The signal distortion type includes at least one; Based on the signal distortion type, match the target signal compensation calculation unit, and generate a corresponding signal compensation scheme in combination with the predicted signal distortion information; Integrate various types of predicted signal distortion information and signal compensation schemes to generate the initial compensation scheme.

7. Audio distortion adjustment device in ship communication equipment, characterized in that The device includes: An environmental trend prediction module, which is used to construct a multi-dimensional environment perception network, obtain the real-time positioning information, real-time environment information, and target route information of the target ship, perform environment trend prediction, and generate an environmental change curve; An environmental scenario extraction module, which is used to perform environmental scenario division and extreme environment extraction based on the environmental change curve, and generate multiple environmental prediction combinations; A signal fluctuation prediction module, which is used to input the multiple environmental prediction combinations into a signal prediction model, match the corresponding signal fluctuation prediction unit, perform signal fluctuation prediction, and obtain a signal fluctuation prediction sequence; An audio signal adjustment module, which is used to perform signal distortion compensation according to the signal fluctuation prediction sequence to generate an initial compensation scheme, and perform dynamic adjustment of the audio signal through an adaptive signal compensation mechanism during the execution of the initial compensation scheme; The environmental trend prediction module is also used to perform the following steps: Construct a multi-dimensional environment perception network, which includes a multi-sensor module and an environmental trend prediction model, and the multi-dimensional environment perception network executes a dynamic progressive prediction mechanism; based on the multi-sensor module, perform multi-source data collection to obtain the real-time positioning information, real-time environment information, and target route information of the target ship; input the real-time positioning information, real-time environment information, and target route information into the environmental trend prediction model for environmental trend prediction, and generate an environmental change curve; The environmental scenario extraction module is also used to perform the following steps: Perform trend analysis on the environmental change curve to identify and obtain multiple environmental feature sets; perform clustering analysis on the multiple environmental feature sets to divide multiple weather scenarios; based on the environmental change curve, extract extreme environmental nodes exceeding the environmental threshold and label them as extreme scenarios; combine the multiple weather scenarios and extreme environmental nodes to generate multiple environmental prediction combinations, and the multiple environmental prediction combinations cover normal and extreme environmental conditions.

Images