A multimodal data communication method and system applying the Beidou satellite system

Abstract

The present invention discloses a multi-modal data communication method and system applying the Beidou satellite system, specifically relating to the technical field of data transmission. During the communication process, it can analyze the time-delay deviation of satellites in different orbits and the influence of environmental factors on signal attenuation, dynamically evaluate the degree of transmission time-delay of satellite signals. Based on the evaluation results, the system divides satellite signals into high-time-delay and low-time-delay signals, and adopts a multi-modal data fusion and signal optimization strategy for high-time-delay signals to effectively reduce the command response error. Combining the signal time-delay characteristics and command response error data, it dynamically adjusts the communication strategy, optimizes the data transmission path, improves the execution efficiency of rescue tasks and the real-time performance of information interaction. The present invention breaks through the limitations of traditional satellite communication modes, enhances the stability, flexibility and intelligence of communication, and can effectively improve the overall response ability of emergency rescue tasks.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and particularly relates to a multi-modal data communication method and system applying the Beidou satellite system. Background Art

[0002] With the rapid development of global satellite communication technology, satellite communication has become an important supporting technology in key fields such as emergency rescue, disaster response, and remote command. As a global satellite navigation and communication system independently developed in China, the Beidou satellite system (BDS) not only has high-precision positioning functions but also can provide short message communication capabilities, and can still maintain smooth communication in extreme environments. However, traditional satellite communication methods mainly rely on single-mode data transmission, which is easily affected by factors such as orbital characteristics, signal attenuation, and communication delay, resulting in a decrease in the transmission efficiency of emergency command information. To solve these problems, multi-modal data communication methods have emerged, which improve communication stability by integrating multiple data transmission modes (such as short messages, data links, and ground networks) to ensure efficient and low-latency information transmission in complex environments.

[0003] The existing technologies have the following deficiencies:

[0004] In the existing satellite communication technology in emergency rescue scenarios, satellite communication links are vulnerable to factors such as orbital delay and signal attenuation in high-dynamic environments, resulting in uncertainties in communication between the command center and rescue units; the traditional single-mode data transmission method lacks flexibility and cannot be effectively optimized for different signal delay situations, which may lead to command response errors. In addition, the existing communication strategies cannot be dynamically adjusted, and it is difficult to optimize the data transmission path according to the real-time transmission state, affecting the timeliness and reliability of information interaction. Therefore, there is an urgent need for a multi-modal data communication method based on the Beidou satellite system, which can make full use of various communication modes of the Beidou satellite to improve the efficiency and accuracy of emergency command data transmission, thereby enhancing the overall rescue response ability. Summary of the Invention

[0005] The purpose of the present invention is to provide a multi-modal data communication method and system applying the Beidou satellite system to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A multi-modal data communication method applying the Beidou satellite system, including the following steps:

[0007] S1: Establish a communication connection between the command center and multiple rescue units through the multi-modal data communication link of the Beidou satellite system;

[0008] S2: After receiving the emergency instruction from the command center, use the communication link of the Beidou satellite system and combine with the multi-modal data transmission technology to transmit the emergency instruction to the rescue unit;

[0009] S3: During the communication process, based on the orbital characteristics of the Beidou satellite system, analyze the delay deviation of different orbital satellites in signal transmission and the influence of environmental factors on signal attenuation, and evaluate the delay degree of satellite signal transmission;

[0010] S4: Based on the evaluation results, divide the satellite signals into high-delay satellite signals and low-delay satellite signals, and adopt the multi-modal data fusion and signal optimization strategy for high-delay satellite signals to reduce the command response error;

[0011] S5: According to the signal transmission delay characteristics of the Beidou satellite system and the on-site command response error data, dynamically adjust the communication strategy and optimize the data transmission path.

[0012] Preferably, in S1, the communication link uses at least one type of satellite among low Earth orbit satellites, medium Earth orbit satellites or geostationary orbit satellites.

[0013] Preferably, in S2, after analyzing the delay deviation situation existing in the signal transmission process of satellites in different orbits, generate a signal delay deviation index. The acquisition method of the signal delay deviation index is as follows:

[0014] Set an interval and the change range of environmental factors Δtenvironment, and according to the pre-set probability distribution, conduct N random samplings to simulate the signal transmission delay situations for multiple times. Each simulation calculates the delay based on different satellite orbital heights and environmental factors;

[0015] For each simulation, extract values from the distribution of each parameter, and then substitute these values into the signal delay model for calculation: ; where i represents the i-th simulation, h(i) and are the values extracted from the corresponding distribution, h is the distance between the satellite and the ground, and c is the speed of light;

[0016] Obtain a set of signal delay values through multiple simulations. The deviation of the delay is defined as the deviation between the simulation result and the theoretical value. Set the theoretical delay as , then the delay deviation is: ; Calculate the signal delay deviation index, and the expression is: ; In the formula, is the signal delay deviation index, and N is the total number of signal delay values.

[0017] Preferably, after analyzing the attenuation degree of satellite signals under environmental factor interference conditions, a signal attenuation anomaly index is generated. The method for obtaining the signal attenuation anomaly index is as follows:

[0018] Prepare input data related to signal attenuation: signal attenuation data , that is, the signal attenuation value measured at each time point; environmental data: air temperature T, humidity H, precipitation P. For each observation point, construct a feature vector: ; Before applying Isolation Forest, use the training dataset to construct an IsolationForest model. Isolate data points through multiple decision trees. Each tree constructs a path by randomly selecting a feature and partitioning the value of the selected feature. Isolation Forest calculates the isolation degree of each data point, that is, the path length by which the data point is isolated in the tree. After training the Isolation Forest model, for each data point, the model generates an anomaly score, indicating the degree of anomaly of the data point. The anomaly score is calculated by the formula: ; where: is the i-th data point The average path length by which it is isolated in all trees, c(n) is a normalization constant, and the formula is: ; n is the total number of data points in the training dataset. The signal attenuation anomaly index is the weighted average of all signal attenuation anomaly scores.

[0019] Preferably, according to the obtained signal delay deviation index and signal attenuation anomaly index, calculate the delay degree value of satellite signal transmission through a machine learning model;

[0020] Convert the signal delay deviation index and signal attenuation anomaly index into a comprehensive feature vector. Use the comprehensive feature vector as the input of the machine learning model. The machine learning model takes predicting the delay degree value label of satellite signal transmission for each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of prediction errors for all satellite signal transmission delay degree value labels as the training target. Train the machine learning model until the sum of prediction errors reaches convergence and then stop the model training. Determine the delay degree value of satellite signal transmission according to the model output result. Among them, the machine learning model is a polynomial regression model.

[0021] Preferably, in S4, based on the evaluation results, divide satellite signals into high-delay satellite signals and high-delay satellite signals. Specifically:

[0022] Compare the obtained time delay degree value of the satellite signal transmission with the reference threshold of the pre-set time delay degree value. If the time delay degree value of the satellite signal transmission is greater than or equal to the reference threshold of the pre-set time delay degree value, it indicates that the time delay degree of the satellite signal transmission is high, and the satellite signal is classified as a high-delay satellite signal; if the time delay degree value of the satellite signal transmission is less than the reference threshold of the pre-set time delay degree value, it indicates that the time delay degree of the satellite signal transmission is low, and the satellite signal is classified as a low-delay satellite signal.

[0023] Preferably, in S5, the on-site command response error is calculated based on the command issuance time, reception time, and response time, specifically as follows:

[0024] The time delay of satellite signal transmission refers to the time difference between the issuance of a command from the command center and the reception of the command by the on-site rescue unit. The expression is: command time difference = command reception time - command issuance time; the command response error refers to the difference between the response time of the on-site rescue unit and the time when it should theoretically start to respond. Response time difference = command response time - (command issuance time + Δt reaction time); where Δt reaction time is the standard response time set according to the task type and command system; the on-site command response error is obtained by calculating the weighted average sum of the command time difference and the response time difference.

[0025] Preferably, the obtained time delay degree value of the satellite signal transmission and the on-site command response error are used as the input items of fuzzy logic, and they are respectively divided into different fuzzy sets;

[0026] The communication strategy is used as the output item of fuzzy logic and is divided into different fuzzy sets;

[0027] Formulate fuzzy rules to describe the influence of the time delay degree value of satellite signal transmission and the definition of on-site command response error on the communication strategy;

[0028] Perform fuzzy reasoning according to the fuzzy rules to dynamically adjust the communication strategy.

[0029] The present invention also provides a multi-modal data communication system applying the Beidou satellite system, including a satellite communication link module, a command transmission module, a time delay evaluation module, a signal optimization strategy module, and a communication strategy dynamic adjustment module;

[0030] Satellite communication link module: Establish a communication connection between the command center and multiple rescue units through the multi-modal data communication link of the Beidou satellite system;

[0031] Command transmission module: After receiving an emergency command from the command center, use the communication link of the Beidou satellite system and combine multi-modal data transmission technology to transmit the emergency command to the rescue unit;

[0032] Time Delay Evaluation Module: During the communication process, based on the orbital characteristics of the Beidou satellite system, analyze the time delay deviation of satellites in different orbits during signal transmission and the impact of environmental factors on signal attenuation, and evaluate the time delay degree of satellite signal transmission;

[0033] Signal Optimization Strategy Module: Based on the evaluation results, divide satellite signals into high-time-delay satellite signals and low-time-delay satellite signals, and adopt multi-modal data fusion and signal optimization strategies for high-time-delay satellite signals to reduce command response errors;

[0034] Communication Strategy Dynamic Adjustment Module: According to the signal transmission time delay characteristics of the Beidou satellite system and the on-site command response error data, dynamically adjust the communication strategy and optimize the data transmission path.

[0035] In the above technical solution, the technical effects and advantages provided by the present invention:

[0036] 1. A multi-modal data communication method and system applying the Beidou satellite system of the present invention effectively improves the stability, real-time performance and adaptability of emergency command communication by constructing a multi-modal data communication link, combining intelligent signal analysis, machine learning prediction and dynamic communication optimization strategies. This method makes full use of various modes such as short message communication and data link communication of the Beidou satellite system, and integrates ground network resources to ensure efficient information transmission in various complex environments (such as disaster areas, maritime rescues, remote uninhabited areas, etc.). Through the calculation and analysis of the signal time delay deviation index and the signal attenuation anomaly index, the present invention can accurately evaluate the quality of satellite signals, and use a machine learning model to predict the time delay, so that the communication strategy can be intelligently adjusted according to the real-time channel state, thereby reducing command response errors and improving the accuracy of task execution.

[0037] 2. The present invention realizes real-time monitoring and dynamic optimization of the communication link quality through the calculation of time delay and signal attenuation anomaly index to ensure the stability of information transmission; secondly, by adopting fuzzy logic reasoning and multi-modal data fusion strategies, the communication system can flexibly adjust the transmission mode according to the actual situation, effectively reducing the impact of high-time-delay satellite signals on rescue command; finally, this method can significantly improve the emergency response efficiency, reduce decision-making errors caused by communication delays, thereby enhancing the coordinated combat ability of rescue tasks and providing strong technical support for various emergency communications and remote commands. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0039] Figure 1 This is the flowchart of the method of the present invention.

[0040] Figure 2 This is the system module diagram of the present invention. Detailed implementation manners

[0041] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] Embodiment 1. Please refer to Figure 1 As shown, a multi-modal data communication method applying the Beidou satellite system in this embodiment includes the following steps:

[0043] S1: Establish a communication connection between the command center and multiple rescue units through the multi-modal data communication link of the Beidou satellite system;

[0044] S2: After receiving the emergency instruction from the command center, use the communication link of the Beidou satellite system and combine with the multi-modal data transmission technology to transmit the emergency instruction to the rescue unit;

[0045] S3: During the communication process, based on the orbital characteristics of the Beidou satellite system, analyze the delay deviation of different orbital satellites in signal transmission and the influence of environmental factors on signal attenuation, and evaluate the delay degree of satellite signal transmission;

[0046] S4: Based on the evaluation results, divide the satellite signals into high-delay satellite signals and low-delay satellite signals, and adopt the multi-modal data fusion and signal optimization strategy for high-delay satellite signals to reduce the command response error;

[0047] S5: Dynamically adjust the communication strategy according to the signal transmission delay characteristics of the Beidou satellite system and the on-site command response error data, and optimize the data transmission path.

[0048] In scenarios such as emergency rescue, disaster response and remote command, the command center needs to maintain efficient and stable communication with multiple rescue units to ensure the rapid response and accurate execution of rescue operations. Traditional single communication modes (such as cellular networks or single satellite links) are vulnerable to signal attenuation, delay fluctuations and link interruptions in complex environments (such as earthquakes, floods, mountains, oceans, etc.), thus affecting the real-time performance and reliability of command and dispatch.

[0049] As China's independently developed global satellite navigation system, the Beidou Satellite System (BDS) not only provides high-precision positioning and timing functions but also has the capabilities of short message communication and two-way data link communication. Among them:

[0050] It supports users to send and receive short messages via Beidou satellites in areas without ground network coverage, and is suitable for low-bandwidth emergency information transmission, such as command sending, location information sharing, etc.

[0051] It supports high-capacity data transmission and can be used for the transmission of real-time voice, video streams and other key data.

[0052] In order to ensure stable communication between the command center and multiple rescue units, the multi-modal data communication link based on the Beidou Satellite System is mainly connected in the following ways:

[0053] The Beidou satellite link is used as the core communication method: the command center establishes direct communication with multiple rescue units through Beidou satellites, which can ensure the stability of information transmission in the event of a ground network failure.

[0054] Integrate ground networks (such as public networks, private networks or self-organizing networks): In the case of ground communication conditions, combine communication methods such as public networks (5G / 4G), self-organizing networks (Wi-Fi, Mesh networks), etc. to enhance the flexibility and reliability of data transmission.

[0055] Short message + data link integration: When the broadband link is limited, use short messages to transmit key information (such as location, status update), and at the same time enable a high-throughput data link to transmit complex data (such as images, videos) when broadband is available.

[0056] Intelligent data shunting: Based on the urgency and bandwidth requirements of the transmitted content, intelligently allocate data to different links. For example, high-priority data with low latency (such as command and dispatch information) can be sent through Beidou short messages or low-latency channels, while information with a large amount of data (such as high-definition videos) can be transmitted through ground networks or satellite broadband.

[0057] Adopt a dynamic link management algorithm to intelligently select the optimal transmission path according to satellite orbital position, signal quality, environmental factors (such as weather, electromagnetic interference), etc. In the case of high latency or link interruption, automatically switch to a low-latency link or an alternative communication mode to ensure that information is not interrupted.

[0058] In emergency rescue missions, the command center needs to transmit instructions to multiple rescue units in real time to ensure the efficient execution of rescue operations. However, in cases where the ground network may be damaged or have insufficient coverage, relying solely on traditional communication methods (such as cellular networks or radio) may not meet the requirements for fast and reliable instruction transmission. Therefore, by utilizing the communication link of the Beidou Satellite System (BDS) and combining it with multi-modal data transmission technology, emergency instructions can be efficiently transmitted in different environments, improving the rescue response speed.

[0059] In emergency rescue scenarios, the command center usually needs to issue various types of instructions to rescue units, such as task arrangements, operation area adjustments, emergency evacuation orders, etc. The transmission of these instructions can be carried out in the following multi-modal ways:

[0060] Applicable scenarios: In cases where the ground network is unavailable or has limited bandwidth, short message communication can ensure the transmission of basic instructions. Transmission content: Includes task adjustment information, GPS coordinates, personnel status reports, etc. Transmission characteristics: Supports a maximum of 1KB data transmission, and can ensure the delivery of emergency information in extreme environments.

[0061] When the command center needs to transmit data such as audio and video, pictures, map information, etc. in real time. Task planning files, geographical information, disaster area images, rescue personnel status data, etc. Supports the transmission of larger amounts of data to ensure that rescue units obtain detailed command information. When the ground network (such as 4G / 5G, Wi-Fi, ad hoc network) is available, the ground network is preferred to improve transmission efficiency. If the ground network experiences signal attenuation or interruption, the system will automatically switch to the Beidou communication link to ensure uninterrupted communication. Low-latency task information is preferentially transmitted via Beidou short messages or the ground network; large amounts of data (such as video, voice) are transmitted via data links or 5G / 4G; important instructions adopt a redundant transmission strategy (i.e., sent through multiple links simultaneously to ensure information delivery).

[0062] To ensure the efficient transmission of emergency instructions, the following optimization technologies are combined to improve communication quality and timeliness: Instructions are prioritized according to their urgency and data type: Level 1 (highest priority): Emergency evacuation instructions, life safety-related information (preferably transmitted via Beidou short messages + ground network). Level 2 (high priority): Task adjustment information, GPS location, voice messages (transmitted via Beidou data link + 4G / 5G). Level 3 (normal priority): Environmental information, non-emergency videos (transmission method selected according to network conditions).

[0063] Dynamic adjustment based on network quality: If the signal attenuation or latency of a certain link is too high, automatically switch to a low-latency link. Bandwidth load balancing: Optimize data distribution to avoid network congestion when multiple links are available. During emergency communication, ensure the confidentiality of instructions by using Beidou encrypted short messages + end-to-end encrypted data transmission to prevent information leakage or tampering.

[0064] S3: The latency of satellite communication is mainly affected by the type of satellite orbit, the distance between the satellite and the ground station, and the signal propagation path. According to different satellite orbit types, there will be significant differences in the signal transmission latency.

[0065] Orbit altitude of low Earth orbit satellites (LEO): LEO satellites are usually located between 500 km and 2000 km above the ground, relatively close to the ground. Due to the low altitude of the satellite, the signal transmission latency is short. The signal round-trip time is usually between 30 milliseconds and 200 milliseconds, which has great advantages for emergency command systems with high real-time requirements. Since LEO satellites usually move at high speeds in orbit, the distance between them and the ground station is constantly changing, which may cause certain fluctuations in latency. Nevertheless, the lower latency of LEO satellites makes them more advantageous in scenarios that require quick response.

[0066] Orbit altitude of medium Earth orbit satellites (MEO): MEO satellites are located in the orbit altitude range of about 8000 km to 20000 km and are usually used in global navigation and communication systems (such as GPS, Galileo). Compared with LEO satellites, the transmission latency of MEO satellites is longer. The signal round-trip time is about 150 milliseconds to 500 milliseconds, depending on the specific orbit position. The signal transmission of MEO satellites is more stable, but still not as low-latency as LEO satellites. MEO satellites usually have higher orbit stability and smaller orbit offsets, so in terms of signal transmission latency, their fluctuations are smaller than those of LEO satellites.

[0067] Orbit altitude of geostationary orbit satellites (GEO): GEO satellites are located at an orbit altitude of about 35786 km and belong to high-orbit satellites. Due to the long distance between GEO satellites and the ground, the signal round-trip latency is high, generally between 500 milliseconds and 700 milliseconds. This may have an impact on some applications that require real-time interaction (such as voice or video calls). Since GEO satellites are relatively stationary and their positions are relatively fixed, the change in latency is small. However, the high latency may lead to command misjudgment or untimely response in some high-risk environments.

[0068] After analyzing the latency deviation of satellites in different orbits during signal transmission, a signal latency deviation index is generated. The method for obtaining the signal latency deviation index is as follows:

[0069] Set an interval (for example, the altitude of LEO satellites ranges from 500 km to 2000 km, and that of GEO satellites is 35786 km), and set its distribution to follow a uniform distribution or a normal distribution.

[0070] Environmental factor Δtenvironment: For example, atmospheric attenuation and weather changes. Set the variation range of environmental factors through historical data or prediction models, and usually set it to follow a normal distribution. According to the set probability distribution, conduct N random samplings to simulate the situation of signal transmission delay multiple times. Each simulation calculates the delay based on different satellite orbital altitudes and environmental factors.

[0071] For each simulation, draw values from the distribution of each parameter, and then substitute these values into the signal delay model for calculation: ; where i represents the i-th simulation, h(i) and are the values drawn from the corresponding distribution, h is the distance between the satellite and the ground, and c is the speed of light.

[0072] Obtain a set of signal delay values through multiple simulations , and the deviation of the delay is defined as the deviation between the simulation result and the theoretical value. For example, set the theoretical delay to be , then the delay deviation is: ; Calculate the signal delay deviation index, and the expression is: ; In the formula, is the signal delay deviation index, N is the total number of signal delay values, and this deviation index represents the average level of signal delay deviation in multiple simulations. If the deviation index is high, it indicates that the uncertainty of signal delay is large, which may affect the real-time performance and stability of the system.

[0073] Satellite signals are interfered by various factors during transmission, such as the atmosphere, climate change, geographical environment, and ground obstacles. These factors will cause signal attenuation and a decline in transmission quality, thereby affecting the change of delay. The influence of environmental factors can be classified into the following categories:

[0074] Atmosphere influence - Troposphere and mesosphere: Satellite signals pass through the Earth's atmosphere during transmission. Water vapor, air pressure changes, and weather systems (such as cyclones, storms, etc.) in the troposphere and mesosphere will cause signal attenuation. When the humidity is high or the temperature changes drastically, the signal attenuation is more significant. Usually, this attenuation is mainly manifested in signals with higher frequencies (such as the Ka band), resulting in a decrease in the signal transmission rate, which may cause fluctuations in the delay.

[0075] Ionospheric influence: The change in the electron density of the ionosphere can also affect the propagation of satellite signals. In particular, the signals of GEO satellites propagate through the ionosphere, and the change in the electron density in the ionosphere may cause signal refraction or reflection, thus increasing the transmission delay. This effect is more obvious in the high-frequency band.

[0076] Meteorological factors - precipitation and clouds: Heavy precipitation (such as rainstorms and thunderstorms) and thick clouds can cause attenuation of satellite signals. In these cases, the satellite signal may be attenuated or even temporarily lose connection, resulting in a sharp increase in delay. Satellite communication systems usually need to have rain fade mitigation technologies to reduce the impact of these factors.

[0077] Snowstorms and hailstorms: These extreme weather conditions will exacerbate signal attenuation, especially at Ka-band frequencies, where the signal attenuation is most significant, which may lead to a decrease in signal quality and instability of the delay.

[0078] Geographical factors and obstacles - terrain and buildings: In complex terrain environments such as cities or mountains, satellite signals may be blocked or reflected by ground buildings, mountains and other obstacles, resulting in signal attenuation or increased delay. In extreme environments, the delay of command transmission may fluctuate significantly, affecting the real-time nature of communication.

[0079] Placement of ground stations and terminal devices: Factors such as the antenna direction and installation location of ground stations and terminals may also affect the quality of satellite signals, and thus affect the delay. If the antenna of the ground station fails to correctly align with the satellite, the signal may be lost, resulting in an increase in delay.

[0080] After analyzing the attenuation degree of satellite signals under environmental factor interference conditions, a signal attenuation anomaly index is generated. The method for obtaining the signal attenuation anomaly index is as follows:

[0081] Prepare input data related to signal attenuation. Signal attenuation data usually consists of multiple environmental factors and time series data, such as meteorological conditions (precipitation, temperature, wind speed, etc.) and the actually measured signal strength attenuation value.

[0082] Signal attenuation data : The signal attenuation value measured at each time point.

[0083] Environmental data: Factors affecting signal attenuation, such as air temperature (T), humidity (H), precipitation (P), etc. For each observation point (i.e., time stamp), construct a feature vector: ; Before applying Isolation Forest, it is usually necessary to standardize or normalize the data, especially when the data has inconsistent dimensions. Through standardization, the mean of each feature is adjusted to 0 and the standard deviation is 1, thus avoiding the excessive influence of certain features on the model results.

[0084] Use the training dataset to build an Isolation Forest model. This model "isolates" data points through multiple decision trees. Each tree constructs a path by randomly selecting a feature and partitioning the values of the selected feature, with the goal of isolating data points as quickly as possible. Isolation Forest calculates the "isolation degree" of each data point, which is the path length by which the data point is isolated in the tree.

[0085] Model training process: Initialization: Set the number of trees (usually 100 or more) and the depth limit of the trees. Build trees: Each tree randomly samples from the dataset and gradually "isolates" each data point. The more trees, the more robust the model. Path length calculation: Each data point is randomly partitioned until it is isolated. The shorter the path length, the easier it is for the data point to be isolated, and it may be an outlier.

[0086] After training the Isolation Forest model, for each data point, the model generates an anomaly score, indicating the degree of anomaly of the data point. Anomaly score The calculation formula is: ; where: is the average path length by which the i-th data point is isolated in all trees, and c(n) is a normalization constant, usually calculated based on the sample size n, with the formula: ; n is the total number of data points in the training dataset. When is close to 1, it indicates that the data point is normal; while when is close to 0, it indicates that the data point is abnormal. The signal attenuation anomaly index is the weighted average of all signal attenuation anomaly scores.

[0087] Based on the obtained signal delay deviation index and signal attenuation anomaly index, calculate the delay degree value of satellite signal transmission through a machine learning model;

[0088] For example, convert the signal delay deviation index and signal attenuation anomaly index into a comprehensive feature vector, use the comprehensive feature vector as the input of the machine learning model, use the machine learning model to predict the delay degree value label of satellite signal transmission for each group of comprehensive feature vectors as the prediction target, use minimizing the sum of prediction errors for all satellite signal transmission delay degree value labels as the training target, train the machine learning model until the sum of prediction errors converges and then stop the model training, and determine the delay degree value of satellite signal transmission according to the model output result. Among them, the machine learning model is a polynomial regression model.

[0089] The method for obtaining the time delay degree value of satellite signal transmission is as follows: Obtain the corresponding function expression from the comprehensive feature vector training data of the trained machine learning model: ; In the formula, is the output function of the model, is the signal time delay deviation index, is the signal attenuation anomaly index, is the time delay degree value of satellite signal transmission.

[0090] S4: Compare the obtained time delay degree value of satellite signal transmission with the reference threshold of the pre-set time delay degree value. If the time delay degree value of satellite signal transmission is greater than or equal to the reference threshold of the pre-set time delay degree value, it indicates that the time delay degree of satellite signal transmission is high, and the satellite signal is classified as a high-delay satellite signal; if the time delay degree value of satellite signal transmission is less than the reference threshold of the pre-set time delay degree value, it indicates that the time delay degree of satellite signal transmission is low, and the satellite signal is classified as a low-delay satellite signal.

[0091] For high-delay satellite signals, the following several signal transmission optimization strategies can be used to reduce the impact of delay:

[0092] Increase the redundancy of the satellite link: For example, use multiple satellite links for communication backup to reduce the delay caused by a single satellite signal problem.

[0093] Adjust the satellite orbit or attitude: Dynamically adjust the orbit or attitude of the satellite according to real-time signal evaluation to optimize the signal transmission path.

[0094] Optimize data encoding and compression algorithms: During signal transmission, adopt efficient encoding and compression algorithms to reduce the amount of data in the signal during transmission, thereby reducing the delay.

[0095] Use low-delay satellites: In the case of high-delay signal transmission, preferentially select low-delay near-earth orbit satellites for signal transmission.

[0096] Dynamically select ground stations: Dynamically select the ground station with the shortest response time for data transmission by real-time evaluating the reception conditions of different ground stations.

[0097] For low-delay satellite signals, the existing communication configuration can be continued to maintain, the system stability can be optimized, and the maintenance cost can be reduced.

[0098] S5: The method for obtaining the on-site command response error data is as follows: When the command center issues an instruction to the site, the issuance time of each instruction will be recorded. This time marks the start moment of the instruction. It can be recorded through the timestamp in the command system. Each time an instruction is issued, the system will automatically record the exact time when the instruction is issued.

[0099] When the on-site rescue unit receives an emergency instruction from the command center, it also records the specific time of receiving the instruction. This time record can accurately reflect the time delay of satellite signal transmission.

[0100] The time from when the rescue unit receives the instruction to when it actually executes the task and responds. The response time is the time mark when the rescue unit starts to act.

[0101] Record the time when the rescue task is completed to measure the accuracy and efficiency of the response time. It can be analyzed in combination with the instruction response time.

[0102] The on-site command response error is calculated based on the instruction issuance time, receiving time, and response time. The specific steps are as follows:

[0103] The time delay of satellite signal transmission refers to the time difference between when the instruction is issued from the command center and when it is received by the on-site rescue unit. The expression is: Instruction time difference = Instruction receiving time - Instruction issuance time;

[0104] The instruction response error refers to the difference between the response time of the on-site rescue unit and the time when it should theoretically start to respond. The theoretical response time can be assumed to be the instruction issuance time plus a predetermined reaction time (set according to factors such as task urgency and personnel familiarity). Response time difference = Instruction response time - (Instruction issuance time + Δt reaction time); where Δt reaction time is the standard response time set according to the task type and command system.

[0105] The on-site command response error is obtained by calculating the weighted average sum of the instruction time difference and the response time difference.

[0106] Take the obtained time delay degree value of satellite signal transmission and the on-site command response error as the input items of fuzzy logic, and take the communication strategy as the output item of fuzzy logic. Dynamically adjust the communication strategy through fuzzy logic to improve the information transmission efficiency between the command center and the rescue unit.

[0107] The time delay degree value of satellite signal transmission (such as the result predicted by a machine learning model) is usually a quantitative value, and we need to convert it into a fuzzy value. Common fuzzy sets can include the following categories: Low Delay, Medium Delay, High Delay;

[0108] The on-site command response error is also a quantitative value, indicating the response deviation caused by signal time delay. We fuzzify it into the following fuzzy sets: Low Error, Medium Error, High Error;

[0109] Through fuzzification, the actual numerical values are mapped to the above-mentioned fuzzy sets. Fuzzification usually uses triangular or trapezoidal membership functions. Taking the "delay degree value" as an example, assuming the range of this value is from 0 to 1000 milliseconds, the specific membership functions can be defined as follows:

[0110] Low delay: The membership degree is high when the delay value is low (0 - 300 milliseconds), and the membership degree of low delay will decrease. Medium delay: Between 300 and 700 milliseconds, the membership degree gradually increases. High delay: The membership degree is high when the delay value is high (700 - 1000 milliseconds), and the membership degree of high delay gradually weakens. Through these membership functions, the delay degree value of satellite signals can be fuzzified into fuzzy sets of "low delay", "medium delay", or "high delay".

[0111] Define a fuzzy rule base according to the delay degree and response error. For example, the rules in the rule base may include: If the delay degree is high delay and the error is high error, then the communication strategy is to optimize the delay. If the delay degree is low delay and the error is low error, then the communication strategy is to keep the current configuration. If the delay degree is medium delay and the error is medium error, then the communication strategy is to perform partial optimization. These rules reflect the selection of communication strategies in different situations.

[0112] The output item of the communication strategy is the target we need to optimize. The output fuzzy set can be defined according to different strategy goals, for example:

[0113] Optimize Delay: Reduce the communication delay, for example, by switching to a low-delay satellite or changing the satellite orbit.

[0114] Keep Current Configuration: Keep the current communication configuration in the case of low error and short delay.

[0115] Partial Optimization: Make appropriate adjustments to the signal delay and response error.

[0116] The output of the communication strategy needs to be represented by a fuzzy set, which usually also involves the definition of membership functions. For example, the degree of delay optimization of the output can be divided into "strong optimization", "medium optimization", and "slight optimization".

[0117] Fuzzy inference is the core of fuzzy logic. It derives the corresponding output (communication strategy) through the fuzzy values of the input items (delay degree and response error) and the rules in the fuzzy rule base.

[0118] Inference is performed based on the fuzzy values of the input items and the fuzzy rules in the rule base. For example, if the inputs are "high latency" and "high error", then according to the fuzzy rule base, the output might be "optimize latency". The inference process generally follows these steps:

[0119] Fuzzify the inputs: Map the actual values of the satellite signal latency degree and the command response error into fuzzy sets.

[0120] Apply the fuzzy rules: Check the combinations of input variables according to the fuzzy rule base and obtain a fuzzy inference result.

[0121] Aggregate the rule results: Aggregate the output results of all rules into a fuzzy set representing the overall communication strategy.

[0122] Defuzzify: Convert the fuzzy output set into an exact communication strategy value. For example, use the Centroid Method to convert the fuzzy output result into a specific numerical communication strategy.

[0123] The defuzzification process converts the fuzzy set obtained from fuzzy inference into a specific communication strategy. Through defuzzification, the communication strategy most suitable for the current situation is obtained.

[0124] Based on the fuzzification results of the satellite signal transmission latency and the command response error each time, the communication strategy is adjusted in real time through the fuzzy inference model. Specifically:

[0125] High latency and high error: When both the latency and the response error are high, the inference result might suggest "optimize latency", such as switching to a low-latency satellite orbit or adopting a signal enhancement strategy.

[0126] Low latency and low error: If both the latency and the error are low, the system might maintain the current communication configuration.

[0127] Medium latency and error: In this case, partial optimization strategies might be adopted, such as adjusting the communication link or enabling a backup signal channel.

[0128] Through continuous monitoring and feedback adjustment, the system can continuously optimize the command response process, reduce command response errors caused by latency and error, and improve the efficiency of emergency command.

[0129] Example 2, please refer to Figure 2 As shown, a multimodal data communication system applying the Beidou satellite system in this embodiment includes a satellite communication link module, a command transmission module, a latency evaluation module, a signal optimization strategy module, and a communication strategy dynamic adjustment module;

[0130] Satellite communication link module: Establish a communication connection between the command center and multiple rescue units through the multi-modal data communication link of the Beidou satellite system;

[0131] Instruction transmission module: After receiving the emergency instruction from the command center, use the communication link of the Beidou satellite system and combine with the multi-modal data transmission technology to transmit the emergency instruction to the rescue unit;

[0132] Delay evaluation module: During the communication process, based on the orbital characteristics of the Beidou satellite system, analyze the delay deviation of different orbital satellites in signal transmission and the influence of environmental factors on signal attenuation, and evaluate the delay degree of satellite signal transmission;

[0133] Signal optimization strategy module: Based on the evaluation results, divide the satellite signals into high-delay satellite signals and low-delay satellite signals, and adopt multi-modal data fusion and signal optimization strategies for high-delay satellite signals to reduce the command response error;

[0134] Communication strategy dynamic adjustment module: Dynamically adjust the communication strategy according to the signal transmission delay characteristics of the Beidou satellite system and the on-site command response error data, and optimize the data transmission path.

[0135] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0136] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations, where A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the front and back associated objects, but it may also represent an "and / or" relationship. Specifically, it can be understood by referring to the context before and after.

[0137] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but this implementation should not be considered to exceed the scope of this application.

[0138] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A multi-modal data communication method using the Beidou satellite system, characterized in that: The following steps are involved: S1: Establish communication connection between the command center and multiple rescue units through the multi-modal data communication link of the Beidou satellite system; S2: After receiving the emergency command from the command center, the emergency command is transmitted to the rescue unit using the communication link of the Beidou satellite system combined with multimodal data transmission technology; S3: During the communication process, based on the orbital characteristics of the BeiDou satellite system, analyze the delay deviation of satellites in different orbits in signal transmission and the impact of environmental factors on signal attenuation, and evaluate the delay degree of satellite signal transmission, specifically: The signal delay deviation index is generated by analyzing the delay deviation of satellites in different orbits during signal transmission. The method for obtaining the signal delay deviation index is as follows: Set an interval and a range of environmental factors Δtenvironmentt, and perform N random samplings according to a pre-set probability distribution to simulate multiple signal transmission delays. Each simulation calculates the delay based on different satellite orbit heights and environmental factors. For each simulation, values ​​are drawn from the distribution of each parameter and then substituted into the signal delay model to calculate: Where i represents the i-th simulation, and is a value drawn from the corresponding distribution, h is the distance between the satellite and the ground, and c is the speed of light; A set of signal delay values ​​are obtained through multiple simulations The delay deviation is defined as the deviation between the simulation result and the theoretical value. The theoretical delay is set to , then the delay deviation for: ; Calculate the signal delay deviation index, the expression is: ; In the formula, is the signal delay deviation index, N is the total number of signal delay values; After analyzing the satellite signal attenuation degree under the interference of environmental factors, the signal attenuation anomaly index is generated. The method for obtaining the signal attenuation anomaly index is as follows: Prepare input data related to signal attenuation: Signal attenuation data , that is, the signal attenuation value measured at each time point; environmental data: temperature T, humidity H, precipitation P, for each observation point, construct a feature vector: ; Before applying Isolation Forest, use the training data set to build an Isolation Forest model. Multiple decision trees are used to isolate data points. Each tree constructs a path by randomly selecting a feature and dividing the value of the selected feature. Isolation Forest calculates the degree of isolation of each data point, that is, the length of the path where the data point is isolated in the tree. After training the Isolation Forest model, for each data point, the model generates an anomaly score, which indicates the degree of abnormality of the data point. The anomaly score The calculation formula is: ;in: is the i-th data point The average path length isolated in all trees, c(n) is a normalization constant, the formula is: ; n is the total number of data points in the training dataset, and the signal attenuation anomaly index is the weighted average of all signal attenuation anomaly scores; According to the acquired signal delay deviation index and signal attenuation anomaly index, the delay value of satellite signal transmission is calculated through a machine learning model; The signal delay deviation index and the signal attenuation anomaly index are converted into a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model predicts the delay degree value label of the satellite signal transmission with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of the prediction errors of the delay degree value labels of all satellite signal transmissions as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The delay degree value of the satellite signal transmission is determined according to the model output result, wherein the machine learning model is a polynomial regression model; S4: Based on the evaluation results, satellite signals are divided into high-latency satellite signals and low-latency satellite signals, and multi-modal data fusion and signal optimization strategies are used for high-latency satellite signals to reduce command response errors; S5: Dynamically adjust the communication strategy and optimize the data transmission path based on the delay value of the satellite signal transmission of the Beidou satellite system and the on-site command response error data.

2. A multimodal data communication method using the BeiDou satellite system according to claim 1, characterized in that: In S1, the communication link uses at least one type of satellite among low earth orbit satellites, medium earth orbit satellites, or geostationary earth orbit satellites.

3. The multimodal data communication method using the BeiDou satellite system according to claim 1, characterized in that: In S4, based on the evaluation results, the satellite signals are divided into high-latency satellite signals and low-latency satellite signals, specifically: The acquired satellite signal transmission delay value is compared with a preset reference threshold of the delay value. If the satellite signal transmission delay value is greater than or equal to the preset reference threshold of the delay value, it indicates that the satellite signal transmission delay degree is high, and the satellite signal is classified as a high-delay satellite signal. If the delay degree value of the satellite signal transmission is less than a preset reference threshold value of the delay degree value, it means that the delay degree of the satellite signal transmission is low, and the satellite signal is classified as a low-delay satellite signal.

4. The multimodal data communication method using the BeiDou satellite system according to claim 1, characterized in that: In S5, the on-site command response error is calculated based on the command issuance time, reception time, and response time, specifically: The delay of satellite signal transmission refers to the time difference between the command issued by the command center and the time when the on-site rescue unit receives the command, and the expression is: command time difference = command reception time − command issuance time; the command response error refers to the difference between the response time of the on-site rescue unit and the time when the response should theoretically start, response time difference = command response time − (command issuance time + Δt reaction time); where Δt reaction time is the standard response time set according to the task type and command system; the on-site command response error is obtained by taking the weighted average sum of the command time difference and the response time difference.

5. The multimodal data communication method using the BeiDou satellite system according to claim 4, characterized in that: The acquired satellite signal transmission delay value and on-site command response error are used as fuzzy logic input items and divided into different fuzzy sets. The communication strategy is taken as the output item of fuzzy logic and divided into different fuzzy sets; Formulate fuzzy rules to describe the impact of satellite signal transmission delay and on-site command response error definition on communication strategy; Perform fuzzy reasoning based on fuzzy rules and dynamically adjust communication strategies.

6. A multimodal data communication system using the BeiDou satellite system, used to implement a multimodal data communication method using the BeiDou satellite system as claimed in any one of claims 1 to 5, characterized in that: It includes satellite communication link module, command transmission module, delay evaluation module, signal optimization strategy module and communication strategy dynamic adjustment module; Satellite communication link module: Establish communication connection between the command center and multiple rescue units through the multi-modal data communication link of the Beidou satellite system; Command transmission module: After receiving the emergency command from the command center, it uses the communication link of the Beidou satellite system and combines multimodal data transmission technology to transmit the emergency command to the rescue unit; Delay evaluation module: During the communication process, based on the orbital characteristics of the Beidou satellite system, the delay deviation of satellites in different orbits in signal transmission and the impact of environmental factors on signal attenuation are analyzed to evaluate the delay degree of satellite signal transmission; Signal optimization strategy module: Based on the evaluation results, satellite signals are divided into high-latency satellite signals and low-latency satellite signals, and multi-modal data fusion and signal optimization strategies are used for high-latency satellite signals to reduce command response errors; Communication strategy dynamic adjustment module: dynamically adjusts communication strategies and optimizes data transmission paths based on the delay value of satellite signal transmission of the Beidou satellite system and the on-site command response error data.

Images