Data acquisition and transmission method and system based on multi-hop cooperation

Abstract

The invention discloses a data acquisition and transmission method and system based on multi-hop cooperation, and relates to the technical field of heat supply system data transmission, and the method comprises the steps: carrying out the initialization of each node of a multi-hop cooperative communication system, and carrying out the channel estimation; collecting data of each node and performing signal classification in combination with signal characteristics, frequency and intensity factors; network state prediction is carried out based on a machine learning technology, and the network state prediction comprises mobility analysis of each node and channel state change trend analysis; and analyzing the resource demand of each node based on the network state prediction result. According to the invention, through intelligent resource allocation and network state prediction, the reliability and efficiency of data transmission are improved, and the mobility of the node and the channel state change trend are predicted, so that the resource allocation strategy is adjusted in advance, the transmission error caused by channel change is reduced, the success rate of data transmission is improved, the transmission delay is reduced, and the user experience is improved. And the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission in a heating system, and in particular to a data collection and transmission method and system based on multi-hop collaboration. Background Art

[0002] In the heating industry, in order to achieve efficient use of energy and sustainable environmental development, remote monitoring of the heating system becomes particularly important. However, traditional data transmission methods may be limited by distance, obstacles or insufficient network coverage, resulting in unstable or delayed data transmission. By introducing multi-hop collaborative data collection and transmission methods into the heating system, data relay transmission can be achieved through collaboration between multiple nodes, thereby breaking through the limitation of the communication distance of a single node and expanding the network coverage.

[0003] In the prior art, multi-hop collaborative communication in a heating system involves collaboration and resource allocation between multiple data nodes. The mobility of each node and changes in channel status can easily lead to deviations in synchronization and channel estimation between nodes, making resource allocation complex and difficult to optimize. Therefore, how to predict network status and resource requirements, and intelligently allocate resources according to real-time network conditions and requirements, thereby improving the accuracy of node synchronization and channel estimation in the heating system, is a problem we need to solve. To this end, a data acquisition and transmission method and system based on multi-hop collaboration are proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a data collection and transmission method and system based on multi-hop collaboration to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: In a first aspect, a data collection and transmission method based on multi-hop collaboration comprises the following steps: Step 1: Initialize each node of the multi-hop cooperative communication system and perform channel estimation to ensure that each node can accurately understand the current channel status, providing a basis for subsequent resource allocation and data transmission; Step 2: Collect data from each node and classify the signal based on signal characteristics, frequency and strength factors; Step 3: Predict the network status based on machine learning technology, where the network status prediction includes the mobility analysis of each node and the channel status change trend analysis; Step 4: Based on the network status prediction results, analyze the resource requirements of each node, and perform intelligent resource allocation according to the resource demand evaluation results to ensure the effective use of resources and the reliability of communication; Step 5: Based on the results of intelligent resource allocation, each node re-transmits data and synchronizes the time between nodes to reduce communication errors caused by synchronization deviation, improve the accuracy of channel estimation, ensure that data can be smoothly transmitted to the target node, and reduce transmission errors caused by changes in channel status.

[0006] A further improvement of the technical solution of the present invention is that in step 1, the process of initializing each node and estimating the channel includes: After the multi-hop cooperative communication system is started, the node status of each node is checked to ensure that each node has the hardware configuration and software environment required for normal operation, check whether the node's power supply, network connection and other infrastructure are normal, and configure a unique identifier for each node, and set communication parameters including transmission power, receiving sensitivity and modulation mode; Through signal exchange and protocol negotiation between nodes, an adjacency relationship is established for each node in the system, and the initialization operation of each node is completed to facilitate data transmission and collaboration; After the node is initialized, it sends a pilot signal for channel estimation. The pilot signal is a known signal sequence that helps the receiving end estimate the channel characteristics and uses the channel estimation algorithm to estimate the channel state information, including the key parameters of the channel gain, phase, and noise power. Each node estimates the channel fading gain based on the received pilot signal and the results of the channel estimation algorithm, and updates its internal channel state information for subsequent resource allocation and data transmission decisions; The node feeds back the estimated channel state information to the adjacent nodes, aggregates, filters and updates the channel state information to obtain the channel state view of the entire network.

[0007] A further improvement of the technical solution of the present invention is that in step 2, the process of signal classification includes: Using multiple acquisition nodes deployed in the target area, each node continuously collects signal data, including the basic characteristics of the signal's amplitude, frequency, and phase, according to the set sampling rate and sampling time; Preprocess the collected signal data, including data cleaning and data formatting; Establish a signal library containing the characteristics, frequency and intensity information of known signals, and analyze the preprocessed signal data to extract signal time domain characteristics, frequency domain characteristics, frequency, intensity, phase and waveform parameters; Different categories of preset signals are matching signals, deviation signals and unknown signals. The extracted signal parameters are compared with the known signals in the signal library, the signal similarity standards are divided, the signal similarity is calculated and the signals are classified; The signal classification and recognition results are further analyzed to mark deviant signals and unknown signals.

[0008] A further improvement of the technical solution of the present invention is that the process of classifying the signal includes: If the signal similarity is greater than or equal to 0.9, it means that the signal similarity is high and is determined to be a matching signal; The signal similarity is between 0.6 and 0.9, which means that the signals are similar but have deviations, and are judged as deviation signals; If the signal similarity is less than 0.6, it means that the signal difference is large and is considered to be an unknown signal.

[0009] A further improvement of the technical solution of the present invention is that in step 3, the process of network status prediction includes: Collecting mobility data and channel state data from each node, and extracting node mobility features and channel state features from the collected data, wherein the node mobility features include speed, acceleration and moving direction, and the channel state features include channel gain, channel phase and noise power; Combine node mobility characteristics and channel status characteristics, use linear regression model to train network status prediction model, adjust model hyperparameters to optimize prediction performance, use cross-validation and other methods to evaluate model performance, and tune the model based on the evaluation results; The new node mobility and channel status feature data are input into the trained network status prediction model, and the mobility trend of each node and the channel status change trend are output.

[0010] A further improvement of the technical solution of the present invention is that the output process of the network status prediction model includes: After extracting the new node mobility and channel state feature data, the node mobility feature and channel state feature are obtained; Format the node mobility features and channel state features into the format required by the model input, and input them into the trained network state prediction model; The network status prediction model analyzes the future mobility trend and channel status change trend of each node based on the input feature data, and then the network status prediction model outputs the prediction results including the mobility trend and channel status change trend of each node.

[0011] A further improvement of the technical solution of the present invention is that in step 4, the process of analyzing the resource requirements of each node includes: Based on the prediction results of node mobility and channel status change trend, combined with business needs and historical resource usage, the future resource demand of each node is evaluated and the trend of future resource demand of each node is analyzed; According to the trend assessment results of each node's future resource demand, analyze the urgency and importance of resource demand and prioritize the resource demand of each node; Based on the resource demand assessment results, formulate resource allocation strategies, including resource scheduling, load balancing and spectrum allocation, to ensure that resources are reasonably allocated to meet the needs of each node and optimize network performance.

[0012] A further improvement of the technical solution of the present invention is that the process of formulating the resource allocation strategy includes: Determine the goal of resource scheduling to balance resource usage, select a resource scheduling algorithm based on priority scheduling, allocate resources to each node, and ensure that key tasks and high-priority services are met first; Monitor the load in the network, identify overloaded or idle nodes, and use a load balancing algorithm based on node status to redistribute traffic to balance network load and improve resource utilization; Analyze the spectrum requirements of each node, comprehensively consider channel conditions, interference level and number of users, and use a spectrum allocation algorithm based on dynamic spectrum access to allocate spectrum resources to each node, optimize spectrum utilization and reduce interference; Monitor network performance in real time, including throughput, latency, and packet loss rate indicators, and adjust resource allocation strategies based on performance monitoring results to adapt to changes in network status and fluctuations in business needs.

[0013] A further improvement of the technical solution of the present invention is that in step 5, the process of each node retransmitting data includes: Apply intelligent resource allocation strategy to the network, allocate resources according to the needs of each node. Based on the intelligent resource allocation results, each node adjusts its own transmission parameters including power and frequency, and uses the network time protocol to synchronize the time between nodes to ensure that the time error between nodes is within an acceptable range, reducing communication errors caused by synchronization deviation. Each node transmits data according to the allocated resources, and during the transmission process, monitors the network status and resource usage in real time to ensure the effectiveness of resource allocation and the reliability of communication; Based on the monitoring results, potential problems are discovered and resolved, and resource allocation strategies are dynamically adjusted to adapt to changes in network status and fluctuations in business demand. A channel quality feedback mechanism is established so that the receiving end feeds back channel quality information to the sending end. The sending end adjusts the data transmission strategy based on the feedback information to optimize transmission performance.

[0014] In a second aspect, a data collection and transmission system based on multi-hop collaboration is used to implement a data collection and transmission method based on multi-hop collaboration, including a multi-hop collaboration communication management platform, wherein the multi-hop collaboration communication management platform is communicatively connected with a data collection module, a signal classification module, a network status prediction module, an intelligent resource allocation module, and a monitoring and adjustment module, wherein electrical signals are connected between the modules; The data acquisition module is used to collect signal data from each node, including basic characteristics of amplitude, frequency and phase, as well as node mobility and channel state information, and pre-process the collected data to provide the system with raw data, which is the basis for subsequent data processing and analysis; The signal classification module is used to extract relevant signal features from the preprocessed data and classify the signals based on the signal similarity calculated based on the features, so that the system can identify and distinguish different types of signals, providing a basis for further processing and resource allocation; The network status prediction module is used to predict the network status including node mobility and channel status change trend, analyze the future status of the network and the resource requirements of each node, provide prediction data support for resource allocation, optimize resource allocation strategy, and improve network performance and efficiency; The intelligent resource allocation module is used to dynamically allocate network resources according to the resource demand prediction results, and perform load balancing and spectrum allocation to ensure that resources are reasonably allocated, meet the needs of each node, optimize network performance, and improve communication reliability; The monitoring and adjustment module is used to monitor the network status and resource usage, dynamically adjust the resource allocation strategy according to the monitoring results, and adjust the data transmission strategy according to the channel quality feedback, so as to improve the adaptability and flexibility of the system, ensure the effectiveness of resource allocation and the reliability of communication, and cope with the changes in network status and the fluctuations in business demand.

[0015] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art: 1. The present invention provides a data collection and transmission method and system based on multi-hop collaboration, which improves the reliability and efficiency of data transmission through intelligent resource allocation and network status prediction, predicts the mobility of nodes and the change trend of channel status, and thus adjusts the resource allocation strategy in advance, reduces transmission errors caused by channel changes, and not only improves the success rate of data transmission, but also reduces transmission delays and improves user experience.

[0016] 2. The present invention provides a data collection and transmission method and system based on multi-hop collaboration, which dynamically adjusts resource allocation according to the actual needs of each node and the network status, thereby optimizing the utilization of network resources. By analyzing historical resource usage and business needs, the future resource needs of each node are predicted, and resources are allocated accordingly, avoiding over-allocation or under-allocation of resources and ensuring the rational use of resources. At the same time, through load balancing and spectrum allocation strategies, resource usage can be further optimized, resource waste can be avoided, and the overall throughput of the network can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 The present invention is a flow chart of the method.

[0019] Figure 2 This is a flow chart for analyzing resource requirements of each node in the present invention.

[0020] Figure 3 It is a module diagram of the present invention.

[0021] Figure 4 It is a flowchart of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Embodiment 1, as Figure 1 As shown, the present invention provides a data collection and transmission method based on multi-hop collaboration, comprising the following steps: Step 1: Initialize each node of the multi-hop cooperative communication system and perform channel estimation to ensure that each node can accurately understand the current channel status and provide a basis for subsequent resource allocation and data transmission. After the multi-hop cooperative communication system is started, check the node status of each node to ensure that each node has the hardware configuration and software environment required for normal operation, check whether the node's power supply, network connection and other infrastructure are normal, and configure a unique identifier for each node. Set communication parameters including transmission power, receiving sensitivity and modulation mode. Through signal exchange and protocol negotiation between nodes, establish an adjacent relationship for each node in the system to complete the initialization operation of each node. After the node is initialized, it sends a pilot signal for channel estimation, where the pilot signal is a known signal sequence used to help the receiving end estimate the channel characteristics and use the channel estimation algorithm to estimate the channel state information, including the key parameters of the channel gain, phase and noise power. Each node estimates the channel fading gain based on the received pilot signal and the result of the channel estimation algorithm, and updates its internal channel state information for subsequent resource allocation and data transmission decisions. The node feeds back the estimated channel state information to the adjacent nodes, aggregates, filters and updates the channel state information, and obtains a channel state view of the entire network.

[0024] Furthermore, the expression for estimating the channel state information is:

[0025] In the formula, For the frequency The estimated channel response at is the number of pilot signals used for estimation, used for averaging processing to improve the accuracy of channel estimation, For the The received power of a pilot signal reflects the power level of the signal at the receiving end after passing through the channel. is the noise power spectrum density, which is a parameter describing the noise intensity. is a frequency variable, used to describe the change of channel response with frequency, For the The delay of a pilot signal reflects the propagation time of the signal in the channel. is the power of the transmitted signal, indicating the power level at the sending end. Is an imaginary unit.

[0026] The expression for estimating channel fading gain is:

[0027] In the formula, for The channel fading gain at time , is the number of multipath components, For the The gain amplitude of a path reflects the attenuation of the signal on this path. For the The Doppler frequency of the path, is the carrier angular frequency, is the power of the transmitted signal, indicating the power level at the sending end. is the noise power spectral density, which is a parameter describing the noise intensity.

[0028] Step 2: Collect data from each node and classify the signal based on signal characteristics, frequency and strength factors. Use multiple collection nodes deployed in the target area. According to the set sampling rate and sampling time, each node continuously collects signal data, including basic characteristics such as signal amplitude, frequency and phase. Preprocess the collected signal data, including data cleaning and data formatting operations. Clean the collected data, remove noise, outliers and duplicate data, ensure the accuracy and reliability of the data, and format the data into a unified format to facilitate subsequent processing and analysis. Establish a signal library containing the characteristics, frequency and strength information of known signals. The signal library can be continuously updated and improved with the addition of new signal data, and the preprocessing is carried out. The processed signal data is analyzed to extract parameters including signal time domain characteristics, frequency domain characteristics, frequency, intensity, phase and waveform. Different categories of signals are preset, namely matching signals, deviation signals and unknown signals. The extracted signal parameters are compared with known signals in the signal library, and the signal similarity is calculated and the signals are classified. Among them, if the signal similarity is greater than or equal to 0.9, it means that the signal similarity is high and it is determined to be a matching signal. If the signal similarity is between 0.6 and 0.9, it means that the signals are similar but there is a deviation and it is determined to be a deviation signal. If the signal similarity is less than 0.6, it means that the signal difference is large and it is considered to be an unknown signal. The classification and recognition results of the signal are further analyzed to mark the deviation signal and the unknown signal.

[0029] Furthermore, the expression of signal similarity is:

[0030] In the formula, For signal and The similarity between is the number of signal samples, and are the two signals to be compared, and Signal and In the The value of the sample points, Indicates signal and In the The square root of the difference between sample points is used to measure the size of the difference. The value range is , the larger the value, the greater the difference. It is a logarithmic function with base 2, which is used to measure the signal and The energy ratio of The value range is The larger the value, the higher the signal The energy relative to the signal The bigger, The value range is , the closer the value is to 1, the smaller the signal difference is. The value range is , the closer the value is to 1, the more similar the signals are.

[0031] Step 3: Predict the network status based on machine learning technology, where the network status prediction includes mobility analysis of each node and channel status change trend analysis, collects mobility data and channel status data from each node, and extracts node mobility features and channel status features from the collected data, where node mobility features include speed, acceleration and moving direction, channel status features include channel gain, channel phase and noise power, combines node mobility features and channel status features, uses a linear regression model to train a network status prediction model, adjusts the model's hyperparameters to optimize the prediction performance, uses cross-validation and other methods to evaluate the model's performance, and performs validation on the model based on the evaluation results. Perform optimization, input the new node mobility and channel state feature data into the trained network state prediction model, output the mobility trend of each node and the channel state change trend, extract the features of the new node mobility and channel state feature data, obtain the node mobility features and channel state features, format the node mobility features and channel state features into the format required for model input, and input them into the trained network state prediction model. The network state prediction model analyzes the future mobility trend and channel state change trend of each node based on the input feature data, and then the network state prediction model outputs the prediction results including the mobility trend and channel state change trend of each node.

[0032] Furthermore, the expression of the mobility trend of each node is:

[0033] In the formula, For The node mobility trend at the moment, is the number of nodes, For the Nodes in The speed of time, For the Nodes in The acceleration of time, For the Nodes in The direction of movement at the moment, is the average value of the moving directions of all nodes, is the standard deviation of the direction difference, The larger the value is, the more obvious the mobility trend of the node is.

[0034] The expression of channel state change trend is:

[0035] In the formula, For The channel status change trend at each moment, For the Nodes in The channel gain at time For the Nodes in The channel phase at time, For the Nodes in The noise power at time, is the average value of noise power of all nodes, is the standard deviation of the noise power difference, The larger the value is, the more obvious the change trend of the channel status is.

[0036] Step 4: Based on the network status prediction results, analyze the resource requirements of each node, and perform intelligent resource allocation based on the resource demand evaluation results to ensure effective resource utilization and communication reliability.

[0037] Step 5: Based on the intelligent resource allocation results, each node re-transmits data and synchronizes the time between nodes to reduce communication errors caused by synchronization deviation, improve the accuracy of channel estimation, ensure that data can be smoothly transmitted to the target node, and reduce transmission errors caused by changes in channel status.

[0038] Embodiment 2, as Figure 2 As shown, based on Example 1, the present invention provides a technical solution: Preferably, in step 4, the process of analyzing the resource requirements of each node includes: Based on the prediction results of node mobility and channel state change trends, combined with business needs and historical resource usage, the future resource needs of each node are evaluated, and the trend of each node's future resource needs is analyzed. According to the evaluation results of the trend of future resource needs of each node, the urgency and importance of resource needs are analyzed, and the resource needs of each node are prioritized. According to the resource demand evaluation results, resource allocation strategies are formulated, including resource scheduling, load balancing and spectrum allocation, to ensure that resources are reasonably allocated to meet the needs of each node and optimize network performance. Among them, the goal of resource scheduling is determined to balance resource usage, and a resource scheduling algorithm based on priority scheduling is selected for each node. Allocate resources to nodes to ensure that key tasks and high-priority services are met first, monitor the load in the network, identify overloaded nodes or nodes with idle resources, adopt a load balancing algorithm based on node status, reallocate traffic to balance network load and improve resource utilization, analyze the spectrum requirements of each node, comprehensively consider channel conditions, interference levels and number of users, adopt a spectrum allocation algorithm based on dynamic spectrum access, allocate spectrum resources to each node, optimize spectrum utilization, reduce interference, monitor network performance in real time, including throughput, delay and packet loss rate indicators, and then adjust the resource allocation strategy based on performance monitoring results to adapt to changes in network status and fluctuations in business needs.

[0039] Furthermore, the trend calculation expression of each node's future resource demand is:

[0040] In the formula, is the trend of future resource demand of each node, is the number of nodes, For the Nodes in The speed of time, For the Nodes in The acceleration of time, For the Nodes in The channel gain at time For the Nodes in The channel phase at time, For the Nodes in The noise power at time, is the average value of noise power of all nodes, The larger the value, the higher the resource demand of the node.

[0041] In step 5, the process of each node retransmitting data includes: Intelligent resource allocation strategy is applied to the network, and resources are allocated according to the needs of each node. Based on the results of intelligent resource allocation, each node adjusts its own transmission parameters including power and frequency, and uses the network time protocol to synchronize the time between nodes to ensure that the time error between nodes is within an acceptable range and reduce communication errors caused by synchronization deviation. Each node transmits data according to the allocated resources, and during the transmission process, the network status and resource usage are monitored in real time to ensure the effectiveness of resource allocation and the reliability of communication. Based on the monitoring results, potential problems are discovered and resolved, and the resource allocation strategy is dynamically adjusted to adapt to changes in network status and fluctuations in business needs. A channel quality feedback mechanism is established to enable the receiving end to feed back channel quality information to the sending end. The sending end adjusts the data transmission strategy based on the feedback information to optimize transmission performance.

[0042] Embodiment 3, as Figure 3 , Figure 4 As shown, on the basis of Examples 1-2, the present invention also provides a data collection and transmission system based on multi-hop collaboration, which is used to implement a data collection and transmission method based on multi-hop collaboration, including a multi-hop collaborative communication management platform, and the multi-hop collaborative communication management platform is communicatively connected with a data collection module, a signal classification module, a network status prediction module, an intelligent resource allocation module and a monitoring and adjustment module, wherein the modules are electrically connected with each other.

[0043] The data acquisition module is used to collect signal data from each node, including basic characteristics of amplitude, frequency and phase, as well as node mobility and channel status information, and pre-process the collected data to provide the system with raw data, which is the basis for subsequent data processing and analysis.

[0044] The signal classification module is used to extract relevant signal features from the preprocessed data and classify the signals based on the signal similarity calculated based on the features, so that the system can identify and distinguish different types of signals, providing a basis for further processing and resource allocation.

[0045] The network status prediction module is used to predict the network status including node mobility and channel status change trends, analyze the future state of the network and the resource requirements of each node, provide prediction data support for resource allocation, optimize resource allocation strategies, and improve network performance and efficiency.

[0046] The intelligent resource allocation module is used to dynamically allocate network resources according to the resource demand prediction results, and perform load balancing and spectrum allocation to ensure that resources are reasonably allocated to meet the needs of each node, optimize network performance, and improve communication reliability.

[0047] The monitoring and adjustment module is used to monitor the network status and resource usage, dynamically adjust the resource allocation strategy according to the monitoring results, and adjust the data transmission strategy according to the channel quality feedback, so as to improve the adaptability and flexibility of the system, ensure the effectiveness of resource allocation and the reliability of communication, and respond to changes in network status and fluctuations in business needs.

[0048] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A data collection and transmission method based on multi-hop collaboration, characterized in that: The following steps are involved: Step 1: Initialize each node of the multi-hop cooperative communication system and perform channel estimation; Step 2: Collect data from each node and classify the signal based on signal characteristics, frequency and strength factors; Step 3: Predict the network status based on machine learning technology, where the network status prediction includes the mobility analysis of each node and the channel status change trend analysis; Step 4: Analyze the resource requirements of each node based on the network status prediction results, and perform intelligent resource allocation according to the resource demand evaluation results; Step 5: According to the intelligent resource allocation result, each node retransmits data and synchronizes the time between the nodes.

2. The data collection and transmission method based on multi-hop collaboration according to claim 1 is characterized in that: In step 1, the process of initializing each node and estimating the channel includes: After the multi-hop cooperative communication system is started, the node status of each node is checked, and a unique identifier is configured for each node, and communication parameters including transmission power, receiving sensitivity and modulation mode are set; Through signal exchange and protocol negotiation between nodes, an adjacency relationship is established for each node in the system, and the initialization operation of each node is completed; After the node is initialized, it sends a pilot signal for channel estimation and uses a channel estimation algorithm to estimate channel state information, including key parameters such as channel gain, phase, and noise power. Each node estimates the channel fading gain based on the received pilot signal and the result of the channel estimation algorithm, and updates its internal channel state information; The node feeds back the estimated channel state information to the adjacent nodes, aggregates, filters and updates the channel state information to obtain the channel state view of the entire network.

3. The data collection and transmission method based on multi-hop collaboration according to claim 2 is characterized in that: In the step 2, the signal classification process includes: Using multiple acquisition nodes deployed in the target area, each node continuously collects signal data, including the basic characteristics of the signal's amplitude, frequency, and phase, according to the set sampling rate and sampling time; Preprocess the collected signal data, including data cleaning and data formatting; Establish a signal library containing the characteristics, frequency and intensity information of known signals, and analyze the preprocessed signal data to extract signal time domain characteristics, frequency domain characteristics, frequency, intensity, phase and waveform parameters; Different categories of preset signals are matching signals, deviation signals and unknown signals. The extracted signal parameters are compared with the known signals in the signal library, the signal similarity standards are divided, the signal similarity is calculated and the signals are classified; The signal classification and recognition results are further analyzed to mark deviation signals and unknown signals.

4. The data collection and transmission method based on multi-hop collaboration according to claim 3 is characterized in that: The process of classifying the signal includes: If the signal similarity is greater than or equal to 0.9, it means that the signal similarity is high and is determined to be a matching signal; The signal similarity is between 0.6 and 0.9, which means that the signals are similar but have deviations, and are judged as deviation signals; If the signal similarity is less than 0.6, it means that the signal difference is large and is considered to be an unknown signal.

5. The method for data collection and transmission based on multi-hop collaboration according to claim 4, characterized in that: In step 3, the process of network status prediction includes: Collecting mobility data and channel state data from each node, and extracting node mobility features and channel state features from the collected data, wherein the node mobility features include speed, acceleration and moving direction, and the channel state features include channel gain, channel phase and noise power; Combine node mobility characteristics and channel status characteristics, use linear regression model to train network status prediction model, adjust model hyperparameters, use cross-validation method to evaluate model performance, and tune the model according to the evaluation results; The new node mobility and channel status feature data are input into the trained network status prediction model, and the mobility trend of each node and the channel status change trend are output.

6. The data collection and transmission method based on multi-hop collaboration according to claim 5 is characterized in that: The output process of the network status prediction model includes: After extracting the new node mobility and channel state feature data, the node mobility feature and channel state feature are obtained; Format the node mobility features and channel state features into the format required by the model input, and input them into the trained network state prediction model; The network status prediction model analyzes the future mobility trend and channel status change trend of each node based on the input feature data, and then the network status prediction model outputs the prediction results including the mobility trend and channel status change trend of each node.

7. The data collection and transmission method based on multi-hop cooperation according to claim 6 is characterized in that: In step 4, the process of analyzing the resource requirements of each node includes: Based on the prediction results of node mobility and channel status change trend, combined with business needs and historical resource usage, the future resource demand of each node is evaluated and the trend of future resource demand of each node is analyzed; According to the trend assessment results of each node's future resource demand, analyze the urgency and importance of resource demand and prioritize the resource demand of each node; Based on the resource demand assessment results, formulate resource allocation strategies, including resource scheduling, load balancing and spectrum allocation.

8. The data collection and transmission method based on multi-hop collaboration according to claim 7 is characterized in that: The process of formulating the resource allocation strategy includes: Determine the goal of resource scheduling to balance resource usage, select a resource scheduling algorithm based on priority scheduling, and allocate resources to each node; Monitor the load in the network, identify overloaded or idle nodes, and use a load balancing algorithm based on node status to redistribute traffic to balance the network load; Analyze the spectrum requirements of each node, comprehensively consider channel conditions, interference level and number of users, and use a spectrum allocation algorithm based on dynamic spectrum access to allocate spectrum resources to each node; Monitor network performance in real time, including throughput, latency, and packet loss rate indicators, and adjust resource allocation strategies based on performance monitoring results to adapt to changes in network status and fluctuations in business needs.

9. The data collection and transmission method based on multi-hop cooperation according to claim 8, characterized in that: In step 5, the process of each node re-transmitting data includes: Apply intelligent resource allocation strategy to the network, allocate resources according to the needs of each node, and based on the intelligent resource allocation results, each node adjusts its own transmission parameters including power and frequency, and uses the network time protocol to synchronize the time between nodes; Each node transmits data according to the allocated resources, and during the transmission process, monitors the network status and resource usage in real time; Based on the monitoring results, potential problems are discovered and resolved, and resource allocation strategies are dynamically adjusted to adapt to changes in network status and fluctuations in business demand. A channel quality feedback mechanism is established so that the receiving end feeds back channel quality information to the sending end, and the sending end adjusts the data transmission strategy based on the feedback information.

10. A data collection and transmission system based on multi-hop collaboration, used to implement the data collection and transmission method based on multi-hop collaboration according to any one of claims 1 to 9, comprising a multi-hop collaboration communication management platform, characterized in that: The multi-hop cooperative communication management platform is communicatively connected with a data acquisition module, a signal classification module, a network status prediction module, an intelligent resource allocation module and a monitoring and adjustment module, wherein the electrical signals between the modules are connected; The data acquisition module is used to collect signal data from each node, including basic characteristics of amplitude, frequency and phase, as well as node mobility and channel state information, and pre-process the collected data; The signal classification module is used to extract relevant signal features from the preprocessed data and classify the signals based on the calculated signal similarity, so that the system can identify and distinguish different types of signals; The network state prediction module is used to predict the network state including node mobility and channel state change trend, and analyze the future state of the network and the resource requirements of each node; The intelligent resource allocation module is used to dynamically allocate network resources according to the resource demand prediction results, and perform load balancing and spectrum allocation; The monitoring and adjustment module is used to monitor the network status and resource usage, dynamically adjust the resource allocation strategy according to the monitoring results, and adjust the data transmission strategy according to the channel quality feedback.

Images