Multi-channel signal transmission method and system based on big data

Abstract

The invention discloses a multi-channel signal transmission method and system based on big data, and aims to improve the signal transmission efficiency and stability, the method comprises the following steps: capturing and preprocessing each channel signal data through a big data platform, and calculating each channel signal purity index; inputting the signal purity index of each channel into a machine learning model, predicting a future state value of each channel, and calculating an expected bandwidth utilization rate of each channel according to the future state value of each channel; obtaining the expected data transmission rate of each channel according to the expected bandwidth utilization rate of each channel; calculating the transmission performance of each channel according to the expected data transmission rate of each channel and the stability of each channel; acquiring signal data to be transmitted, determining transmission requirements, selecting a plurality of channels with transmission performance meeting the transmission requirements, and transmitting the signal data to be transmitted through the selected channels; according to the invention, key technical problems can be effectively solved, and signal transmission requirements in different scenes can be met.

Description

Technical Field

[0001] The present invention relates to the fields of communication technology, big data analysis, and machine learning, and in particular to a multi-channel signal transmission method and system based on big data. Background Art

[0002] With the rapid development of information technology, the demand for data transmission continues to grow. How to transmit signals efficiently and stably has become a key issue. In traditional signal transmission, there is often a lack of accurate analysis and prediction of channel status, resulting in low transmission efficiency and poor stability.

[0003] At present, big data technology and machine learning models have brought new solutions to signal transmission. Through the big data platform, the signal data of each channel can be captured and preprocessed to fully understand the current state of the channel. Using the machine learning model, the future state value of each channel can be predicted based on the channel signal purity index, and then the expected bandwidth utilization and data transmission rate can be calculated. This makes it possible to plan the signal transmission path in advance and improve transmission efficiency.

[0004] At the same time, considering channel stability is crucial for signal transmission. Selecting a channel based solely on the data transmission rate may lead to instability during transmission. Therefore, calculating the transmission performance by comprehensively considering the expected data transmission rate and stability of the channel can more accurately select the channel that is most suitable for transmitting signals.

[0005] In practical applications, different signal data to be transmitted have different transmission requirements. By selecting a channel whose transmission performance meets the requirements for transmission, high-quality and efficient transmission of the signal can be ensured to meet the growing communication needs. Summary of the invention

[0006] The present invention provides a multi-channel signal transmission method and system based on big data, comprising:

[0007] S10, capturing and preprocessing the signal data of each channel through the big data platform, and calculating the purity index of the signal of each channel;

[0008] S20, inputting the signal purity index of each channel into the machine learning model respectively, predicting the future state value of each channel, and calculating the expected bandwidth utilization of each channel according to the future state value of each channel;

[0009] S30, deriving an expected data transmission rate of each channel according to the expected bandwidth utilization of each channel;

[0010] S40, calculating the transmission performance of each channel according to the expected data transmission rate of each channel and the stability of each channel;

[0011] S50, obtaining signal data to be transmitted, determining transmission requirements, selecting several channels whose transmission performance meets the transmission requirements, and transmitting the signal data to be transmitted through the selected channels;

[0012] The multi-channel signal transmission method based on big data as described above is characterized in that the signal data of each channel is captured and preprocessed by a big data platform, and the purity index of each channel signal is calculated, including the following sub-steps:

[0013] Use the collection function of the big data platform to collect signal data of each channel in real time;

[0014] By denoising and normalizing the signal data collected by the big data platform, the signal data is normalized to a specific value range;

[0015] The signal purity index of each channel is calculated by comprehensively considering the signal strength and frequency characteristics.

[0016] The multi-channel signal transmission method based on big data as described above is characterized in that the signal purity index of each channel is input into the machine learning model respectively, the future state value of each channel is predicted, and the expected bandwidth utilization of each channel is calculated according to the future state value of each channel, including the following sub-steps:

[0017] Select a support vector machine model, and input the preprocessed signal purity index of each channel into the selected machine learning model;

[0018] The model predicts the state value of each channel in the future based on the input data;

[0019] Based on the predicted future state value of each channel, a specific calculation formula is used to calculate the expected bandwidth utilization of each channel.

[0020] The multi-channel signal transmission method based on big data as described above is characterized in that the expected data transmission rate of each channel is obtained according to the expected bandwidth utilization of each channel, and includes the following sub-steps:

[0021] Determine a relationship formula between expected bandwidth utilization and expected data transmission rate, and substitute the expected bandwidth utilization of each channel into the relationship formula;

[0022] The expected data transmission rate for each channel is calculated.

[0023] The multi-channel signal transmission method based on big data as described above is characterized in that the transmission performance of each channel is calculated according to the expected data transmission rate of each channel and the stability of each channel, and includes the following sub-steps:

[0024] Evaluate the stability of each channel by monitoring channel parameters such as bit error rate, packet loss rate and delay;

[0025] The transmission performance of each channel is calculated by combining the expected data transmission rate and stability evaluation results of each channel.

[0026] The multi-channel signal transmission method based on big data as described above is characterized in that a plurality of channels whose transmission performance meets the transmission requirements are selected, including the following sub-steps:

[0027] Determine the evaluation indicators and weights of transmission performance;

[0028] Calculate the comprehensive transmission performance score of each channel based on the evaluation indicators and weights;

[0029] Sort each channel according to the comprehensive transmission performance score;

[0030] The number of channels to be selected is determined based on transmission requirements.

[0031] The multi-channel signal transmission method based on big data as described above is characterized in that the signal data to be transmitted is transmitted through the selected channel, comprising the following sub-steps:

[0032] Determine the method of signal segmentation;

[0033] Allocating the divided signal data to the selected multiple channels for parallel transmission;

[0034] At the receiving end, the transmitted signal data is reassembled according to the segmentation order and rules;

[0035] Check the integrity and correctness of the reassembled signal data.

[0036] The multi-channel signal transmission system based on big data as described above is characterized by comprising:

[0037] Data preprocessing module: Capture and preprocess the signal data of each channel through the big data platform, and calculate the purity index of each channel signal;

[0038] Prediction module: Input the signal purity index of each channel into the machine learning model, predict the future state value of each channel, and calculate the expected bandwidth utilization of each channel based on the future state value of each channel;

[0039] Data transmission rate calculation module: derives the expected data transmission rate of each channel according to the expected bandwidth utilization of each channel;

[0040] Transmission performance evaluation module: calculates the transmission performance of each channel based on the expected data transmission rate of each channel and the stability of each channel;

[0041] Signal transmission module: obtains signal data to be transmitted, determines transmission requirements, selects several channels whose transmission performance meets the transmission requirements, and transmits the signal data to be transmitted through the selected channels;

[0042] A computer storage medium as described above, characterized in that it comprises: at least one memory and at least one processor;

[0043] A memory for storing one or more program instructions;

[0044] A processor is used to run one or more program instructions to execute a multi-channel signal transmission method based on big data as described in any one of the above items.

[0045] The beneficial effects achieved by the present invention are as follows:

[0046] (1) Improve transmission efficiency

[0047] The signal data of each channel is captured and preprocessed through the big data platform, the channel signal purity index is accurately calculated, and then the machine learning model is used to predict the future state value of each channel, thereby deriving the expected bandwidth utilization and data transmission rate. This enables the system to select the optimal transmission path based on the actual situation of the channel, greatly improving data transmission efficiency and reducing transmission time and resource waste.

[0048] (2) Enhance transmission stability

[0049] While considering the expected data transmission rate of the channel, the stability of each channel is comprehensively evaluated and the transmission performance is calculated. In this way, when selecting the transmission channel, not only the transmission speed is paid attention to, but also the stability of the channel is emphasized, thereby effectively avoiding data loss, interruption and other problems caused by channel instability during the transmission process, and enhancing the stability and reliability of signal transmission.

[0050] (3) Meet different transmission requirements

[0051] According to the different transmission requirements of the signal data to be transmitted, a channel with transmission performance that meets the requirements is selected for transmission. This enables the present invention to adapt to various types of signal transmission tasks. Whether it is a video stream with high real-time requirements or a file transmission with high accuracy requirements, the most suitable channel can be found, thereby improving the adaptability and flexibility of the system.

[0052] (4) Promote the development of communication technology

[0053] The present invention combines advanced technologies such as big data and machine learning to provide an innovative solution for signal transmission. It provides new ideas and methods for the development of the communications field, and is expected to promote the continuous advancement of communications technology and meet people's growing communications needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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.

[0055] Figure 1 This is a multi-channel signal transmission method and system flow chart based on big data provided in an embodiment of the present application.

[0056] Figure 2 It is a schematic diagram of a multi-channel signal transmission method and system based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present invention are 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, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0058] Embodiment 1

[0059] like Figure 1 As shown, the embodiment of the present application is a multi-channel signal transmission method and system based on big data, including:

[0060] Step S10: De-noising and normalizing the signal data collected by the big data platform to normalize the signal data to a specific value range;

[0061] The process of capturing and preprocessing the signal data of each channel through the big data platform and calculating the signal purity index of each channel mainly includes: firstly, collecting the original signal data from each channel, then performing preprocessing operations such as denoising and format unification on these data, then extracting key features such as frequency characteristics, and finally using these features to calculate the purity index reflecting the signal quality, including the following sub-steps:

[0062] Step S11: using the acquisition function of the big data platform to collect signal data of each channel in real time;

[0063] First, ensure that the acquisition system establishes a stable and reliable connection with each channel. By configuring appropriate interfaces and protocols, the big data platform can accurately receive signals from different channels. During the acquisition process, a high-frequency sampling method is adopted to ensure that subtle changes and dynamic characteristics of the signal can be captured. At the same time, in order to improve the acquisition efficiency and data accuracy, a data caching mechanism is set up. When the network experiences short-term fluctuations or other abnormal conditions, data can be temporarily stored and continued to be transmitted after conditions return to normal. A real-time monitoring mechanism is established to monitor the data quality and transmission status during the acquisition process at any time, and make timely adjustments and repairs if problems are found.

[0064] Step S12: De-noising and normalizing the signal data collected by the big data platform to normalize the signal data to a specific value range;

[0065] A combination of multiple denoising algorithms is used to first remove the more obvious random noise, and then further eliminate interference with noise of specific frequencies. In the normalization process, the appropriate target value range is first determined, and the normalized proportional factor is calculated based on the statistical characteristics of the signal data, such as maximum, minimum, and mean values. For each collected signal data point, a linear transformation is performed according to the proportional factor to make it fall within a specific value range. At the same time, the data changes during the processing process are continuously monitored to ensure that the normalized signal data not only retains the characteristics of the original signal, but can also be processed more stably and efficiently in subsequent calculations and analyses.

[0066] Step S13, comprehensively considering the signal strength and frequency characteristics, and calculating the signal purity index of each channel;

[0067] Analyze the intensity distribution of the signal, and determine its intensity variation range and mean value by measuring the amplitude value of the signal at different time points. According to the pre-set algorithm and weight distribution, comprehensively calculate the various indicators of signal intensity and frequency characteristics. For example, different weight coefficients can be assigned to the intensity index and different frequency characteristic indicators, and adjusted according to their importance. By calculating these indicators, the purity index of each channel signal is obtained. In order to calculate the purity index of each channel signal after preprocessing, a more complex model is constructed. The model takes into account the signal-to-noise ratio, signal stability, and continuity of the signal. The following formula is used to calculate the purity index of each channel signal:

[0068]

[0069] Among them, P i Represents the purity index of the i-th channel signal; ω SNR represents the weight coefficient related to the signal-to-noise ratio, reflecting the influence of the ratio of signal to noise on purity; represents the signal strength of the i-th channel; Ni represents the noise intensity of the i-th channel; Represents the signal-to-noise ratio decibel value used to calculate signal i. By multiplying by 10 and taking the logarithm, a signal-to-noise ratio value in decibels is obtained; ω stab represents the weight coefficient related to signal stability; M represents the number of sampling points; m represents a certain number or time segment index step; S m Indicates the signal value of the mth segment; Represents the average value of the signal; S m+1 and S m Respectively represent the signal strength values ​​of two adjacent sampling points; ω cont Represents the weight coefficient related to signal continuity, different weight coefficients ω SNR ,ω stab and ω cont It can be adjusted according to specific application scenarios and needs to highlight the importance of different factors to purity.

[0070] S20, inputting the signal purity index of each channel into the machine learning model respectively, predicting the future state value of each channel, and calculating the expected bandwidth utilization of each channel according to the future state value of each channel, specifically including the following sub-steps:

[0071] Step S21, selecting a support vector machine model, and inputting the preprocessed purity index of each channel signal into the selected machine learning model;

[0072] The purity index of each channel signal after preprocessing is used as input feature, and a model with an appropriate kernel function is used to train on the training data set. The optimal hyperparameters are selected through cross-validation to ensure that the model has good generalization ability.

[0073] Step S22: The model predicts the state value of each channel in the future based on the input data;

[0074] First, the channel signal purity index in the historical data needs to be preprocessed, including cleaning, standardization and feature engineering; then, the preprocessed data is used to train the model, select the appropriate kernel function and adjust the hyperparameters to optimize the model performance; after the model training is completed and passed the validation set test, the latest channel purity data can be input to let the model predict the state value of each channel in the future period of time

[0075] Step S23: Based on the predicted future state value of each channel, using a specific calculation formula, calculate the expected bandwidth utilization of each channel;

[0076] Based on the future state value predicted by the machine learning model, data related to signal strength, quantity and bandwidth utilization calculation are collected, useful features are extracted from these data and feature vectors are constructed. Based on the feature vectors and historical data, a formula is constructed to calculate the expected bandwidth utilization of each channel, providing a decision-making basis for network management. The following formula is used to calculate the expected bandwidth utilization:

[0077]

[0078] Among them, U i represents the expected bandwidth utilization of the ith channel; N represents the total number of channels; B i represents the predicted state value of the i-th channel; S i The signal strength of the i-th channel; P i The purity index represented by is calculated in the previous step; β is an adjustment factor used to balance the impact of the fluctuation of the predicted state value on the bandwidth utilization. By adjusting β, the weight of the fluctuation term in the entire formula can be controlled; Represents the average value of all channel prediction state values.

[0079] Step S30, deriving the expected data transmission rate of each channel according to the expected bandwidth utilization of each channel; specifically comprises the following sub-steps:

[0080] Step S31, determining a relationship formula between expected bandwidth utilization and expected data transmission rate, and substituting the expected bandwidth utilization of each channel into the relationship formula;

[0081] Step S32, obtaining the expected data transmission rate of each channel by calculation;

[0082] According to the expected bandwidth utilization of each channel obtained previously, these utilization values ​​are multiplied by the total bandwidth of the corresponding channel to calculate the expected data transmission rate of each channel. Assuming that the expected data transmission rate is R, the expected data transmission rate is calculated using the following formula:

[0083]

[0084] Where R is the expected data transmission rate of the channel; α and β are adjustment factors used to balance the impact of different factors on the expected data transmission rate; U i is the expected bandwidth utilization of the ith channel; R max，i represents the maximum theoretical transmission rate of the ith channel; P i is the purity index of the ith channel; α·U i ·R max，i ·P i Indicates the expected bandwidth utilization U i The maximum theoretical transmission rate R max，i And the purity index Pi The product of the two, multiplied by an adjustment factor α, reflects the data transmission rate that the channel can achieve under ideal conditions, and the purity index P i The introduction of enhances the consideration of channel quality; β in the formula is another adjustment factor used to balance the weighted terms in the denominator. i When P is higher, the denominator decreases, thereby increasing the expected data transmission rate R; conversely, when P i When it is lower, the denominator increases, causing R to decrease.

[0085] Step S40, calculating the transmission performance of each channel according to the expected data transmission rate of each channel and the stability of each channel;

[0086] Comprehensively consider the two factors of data transmission rate and channel stability to evaluate the performance and capabilities of each channel in actual transmission, so as to provide a basis for decisions such as selecting the optimal channel or allocating channel resources. The specific steps include the following:

[0087] Step S41, evaluating the stability of each channel by monitoring channel parameters such as bit error rate, packet loss rate and delay;

[0088] Collect the bit error rate E of each channel periodically or periodically i , Packet loss rate L i and delay D i data; secondly, combined with the previously calculated expected data transmission rate R and expected bandwidth utilization U i , and the channel purity index P i , the following formula is used to evaluate the stability of each channel:

[0089]

[0090] Among them, S i represents the channel stability evaluation formula; R represents the expected data transmission rate of the channel, and a higher data rate means a faster transmission speed; U i represents the expected bandwidth utilization, a higher bandwidth utilization means that the channel is fully utilized; P i Indicates the purity index of the channel, indicating the degree of interference to the channel signal. The higher the purity index, the less interference the signal receives and the higher the signal quality. i Indicates the channel bit error rate. The higher the bit error rate, the lower the reliability of data transmission. i Indicates the packet loss rate of the channel. The higher the packet loss rate, the worse the integrity of data transmission. i Indicates the channel delay, which is the time required for a data packet to reach the receiving end from the sending end. The longer the delay, the lower the efficiency of data transmission. i) takes into account the channel purity index P i , the natural logarithm ln is used to reflect the importance of the purity index. The higher the purity index, the higher the stability score.

[0091] Step S42: Combine the expected data transmission rate and stability evaluation results of each channel and use the formula To evaluate the transmission performance of each channel, where X i represents the channel transmission performance; R represents the data transmission rate; S i Indicates the stability of the channel; U i is the bandwidth utilization; α is a weight factor used to adjust the importance of bandwidth utilization, and compare and select the optimal channel through calculation.

[0092] Step S50, obtaining signal data to be transmitted, determining transmission requirements, selecting several channels whose transmission performance meets the transmission requirements, and transmitting the signal data to be transmitted through the selected channels, specifically includes the following sub-steps:

[0093] Step S51, determining the evaluation index and weight of transmission performance;

[0094] Identify the performance indicators that are important for a specific transmission task, such as throughput, bit error rate, latency, signal-to-noise ratio, spectrum efficiency, and energy consumption. Then, assign a weight value to each selected performance indicator. The weight can be determined through expert opinions and historical data analysis.

[0095] Step S52: Calculate the comprehensive transmission performance score of each channel according to the evaluation index and weight;

[0096] According to the performance indicators and corresponding weights defined in the previous step, use an appropriate mathematical model to calculate the comprehensive performance score of each channel. Assume that there are n different performance indicators and each indicator i corresponds to a score Y i , and a weight W i , where 0≤W i ≤10≤W i ≤1, and the sum of all weights is 1, that is, Using formula Among them, P s is the transmission performance score; W i is the weight of indicator i; Y i is the score of the channel on index i.

[0097] Step S53, sorting each channel according to the comprehensive transmission performance score;

[0098] The channels are sorted by these scores to ensure that the channels are ranked from highest to lowest or lowest to highest in terms of their performance.

[0099] Step S54, determining the number of channels to be selected according to transmission requirements;

[0100] When clarifying the specific transmission requirements of the signal data to be transmitted, the data volume can be determined by analyzing the signal source, understanding the data generation rules and rate, and counting the data volume over a period of time, while considering the possibility of data compression; the transmission time limit needs to be analyzed in the application scenario requirements and the receiving end requirements, communicate with relevant parties, and consider network conditions and transmission distances; the priority is determined based on the importance of the data, the degree of business impact, etc., and a priority evaluation system is established to ensure that high-priority data is transmitted first and resources are allocated reasonably.

[0101] Embodiment 2

[0102] like Figure 2 As shown, Embodiment 2 of the present application provides a multi-channel signal transmission system based on big data, including:

[0103] Data preprocessing module 21: Capture and preprocess the signal data of each channel through the big data platform, and calculate the purity index of each channel signal, including the following submodules:

[0104] Data acquisition submodule 211: using the acquisition function of the big data platform to collect signal data of each channel in real time;

[0105] Data preprocessing submodule 212: A combination of multiple denoising algorithms is used to first remove more obvious random noise, and then further eliminate interference with noise of specific frequencies. In the normalization process, a suitable target value range is first determined, and the normalized proportional factor is calculated based on the statistical characteristics of the signal data, such as maximum value, minimum value, mean value, etc. For each collected signal data point, a linear transformation is performed according to the proportional factor so that it falls within a specific value range. At the same time, the data changes during the processing process are continuously monitored to ensure that the normalized signal data not only retains the characteristics of the original signal, but can also be processed more stably and efficiently in subsequent calculations and analyses.

[0106] Data quality assessment submodule 213: Calculate the purity index of each channel signal after preprocessing; In order to calculate the purity index of each channel signal after preprocessing, a more complex model is constructed, which not only considers the signal-to-noise ratio of the signal, but also considers the influence of the stability, continuity, and other factors of the signal. The following formula is used to calculate the purity index of each channel signal:

[0107]

[0108] Among them, P i Represents the purity index of the i-th channel signal; ω SNRrepresents the weight coefficient related to the signal-to-noise ratio, reflecting the influence of the ratio of signal to noise on purity; Si represents the signal strength of the i-th channel; N i represents the noise intensity of the i-th channel; Represents the signal-to-noise ratio decibel value used to calculate signal i. By multiplying by 10 and taking the logarithm, a signal-to-noise ratio value in decibels is obtained; ω stab represents the weight coefficient related to signal stability; M represents the number of sampling points; m represents a certain number or time segment index step; S m Indicates the signal value of the mth segment; Represents the average value of the signal; S m+1 and S m Respectively represent the signal strength values ​​of two adjacent sampling points; ω cont Represents the weight coefficient related to signal continuity, different weight coefficients ω SNR ,ω stab and ω cont It can be adjusted according to specific application scenarios and needs to highlight the importance of different factors to purity.

[0109] Prediction module 22: Input the signal purity index of each channel into the machine learning model, predict the future state value of each channel, and calculate the expected bandwidth utilization of each channel according to the future state value of each channel, including the following sub-modules:

[0110] Data input and model application submodule 221: input the signal purity index of each channel into the machine learning model; determine the collection method and frequency of the signal purity index, continuously collect the data of each channel through professional equipment, software tools or sensors, and then screen and clean the collected data to remove outliers and erroneous data to ensure accuracy and reliability, then organize and format the data, store it in a specific data format and mark the corresponding channel information, and finally select a suitable machine learning model based on the specific application requirements and data characteristics to prepare for inputting the signal purity index of each channel into the model.

[0111] Model training and prediction submodule 222: The machine learning model is trained based on the signal purity index of each channel and is used to predict the state value of each channel in the future; the signal purity index data of each channel is continuously collected, and these data are strictly screened, cleaned and formatted to remove outliers and erroneous data to ensure the accuracy and reliability of the data. Then, according to actual needs and data characteristics, a suitable machine learning algorithm is selected, such as a neural network, a random forest, etc., and the model is trained using the prepared purity index data. The parameters of the model are continuously adjusted to improve the accuracy of the prediction. During the training process, the data is divided into a training set and a test set, and the performance of the model is evaluated through the test set. When the model training is completed, the new channel signal purity index can be input into the model to predict the state value of each channel in the future.

[0112] Result evaluation and decision support submodule 223: Calculate the expected bandwidth utilization of each channel according to the future state value of each channel output by the machine learning model; Based on the future state value predicted by the machine learning model, collect data related to bandwidth utilization calculation including transmission rate, signal strength, etc., extract useful features from these data and construct feature vectors, select appropriate calculation methods, construct formulas based on feature vectors and historical data, calculate the expected bandwidth utilization of each channel, provide decision-making basis for network management, and use the following formula to calculate the expected bandwidth utilization:

[0113]

[0114] Among them, U i represents the expected bandwidth utilization of the ith channel; N represents the total number of channels; B i represents the predicted state value of the i-th channel; S i The signal strength of the i-th channel; P i The purity index represented by is calculated in the previous step; β is an adjustment factor used to balance the impact of the fluctuation of the predicted state value on the bandwidth utilization. By adjusting β, the weight of the fluctuation term in the entire formula can be controlled; Represents the average value of all channel prediction state values.

[0115] The data transmission rate calculation module 23 is used to calculate the expected data transmission rate of each channel according to the expected bandwidth utilization of each channel, and includes the following submodules:

[0116] Application and prediction submodule 231: Based on the expected bandwidth utilization of each channel, the expected data transmission rate of each channel is calculated using a preset mathematical model; it is necessary to first determine the channel set and collect the expected bandwidth utilization data, clarify the preset mathematical model, obtain the utilization value and total bandwidth value of each channel, use the mathematical model to calculate, and then verify the rationality of the result, adjust and record it if necessary, and at the same time, continuously monitor the channel usage, regularly update the data to recalculate the expected data transmission rate, and optimize the allocation of network resources.

[0117] Selection and configuration submodule 232: the mathematical model is a linear regression model;

[0118] Calculation and decision making submodule 233: The expected data transmission rate is calculated based on the expected bandwidth utilization and other relevant factors; based on the expected bandwidth utilization of each channel obtained previously, these utilization values ​​are multiplied by the total bandwidth of the corresponding channel to calculate the expected data transmission rate of each channel. Assuming that the expected data transmission rate is R, the expected data transmission rate is calculated using the following formula:

[0119]

[0120] Where R is the expected data transmission rate of the channel; α and β are adjustment factors used to balance the impact of different factors on the expected data transmission rate; U i is the expected bandwidth utilization of the ith channel; R max，i represents the maximum theoretical transmission rate of the ith channel; P i is the purity index of the ith channel; α·U i ·R max，i ·P i Indicates the expected bandwidth utilization U i The maximum theoretical transmission rate R max，i And the purity index P i The product of the two, multiplied by an adjustment factor α, reflects the data transmission rate that the channel can achieve under ideal conditions, and the purity index P i The introduction of enhances the consideration of channel quality; β in the formula is another adjustment factor used to balance the weighted terms in the denominator. i When P is higher, the denominator decreases, thereby increasing the expected data transmission rate R; conversely, when P i When it is lower, the denominator increases, causing R to decrease.

[0121] Transmission performance evaluation module 24: Calculates the transmission performance of each channel according to the expected data transmission rate of each channel and the stability of each channel, including the following sub-modules:

[0122] Stability assessment and historical data analysis submodule 241: Regularly collect the bit error rate E of each channel i , Packet loss rate L i and delay D i data; secondly, combined with the previously calculated expected data transmission rate R and expected bandwidth utilization U i , and the channel purity index P i , the following formula is used to evaluate the stability of each channel:

[0123]

[0124] Among them, S i represents the channel stability evaluation formula; R represents the expected data transmission rate of the channel, and a higher data rate means a faster transmission speed; U i represents the expected bandwidth utilization, a higher bandwidth utilization means that the channel is fully utilized; P i Indicates the purity index of the channel, indicating the degree of interference to the channel signal. The higher the purity index, the less interference the signal receives and the higher the signal quality. i Indicates the channel bit error rate. The higher the bit error rate, the lower the reliability of data transmission. i Indicates the packet loss rate of the channel. The higher the packet loss rate, the worse the integrity of data transmission. i Indicates the channel delay, which is the time required for a data packet to reach the receiving end from the sending end. The longer the delay, the lower the efficiency of data transmission. i ) takes into account the channel purity index P i , the natural logarithm ln is used to reflect the importance of the purity index. The higher the purity index, the higher the stability score.

[0125] Transmission performance calculation submodule 242: Combine the expected data transmission rate and stability evaluation results of each channel, and use the formula To evaluate the transmission performance of each channel, where X i represents the channel transmission performance; R represents the data transmission rate; S i Indicates the stability of the channel; U i is the bandwidth utilization; α is a weight factor used to adjust the importance of bandwidth utilization, and compare and select the optimal channel through calculation.

[0126] Feedback and optimization module 25: obtains signal data to be transmitted, determines transmission requirements, selects several channels whose transmission performance meets the transmission requirements, and transmits the signal data to be transmitted through the selected channels, including the following submodules:

[0127] Signal data acquisition submodule 251: acquires signal data to be transmitted;

[0128] Transmission demand determination submodule 252: Clarify the specific transmission requirements of the signal data to be transmitted. The data volume can be determined by analyzing the signal source, understanding the data generation rules and rate, and counting the data volume within a period of time, while considering the possibility of data compression; the transmission time limit needs to analyze the application scenario requirements and the receiving end requirements, communicate with relevant parties and consider the network conditions and transmission distance; the priority is determined based on the importance of the data, the degree of business impact, etc., and a priority evaluation system is established to ensure that high-priority data is transmitted first and resources are allocated reasonably.

[0129] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor;

[0130] The memory is used to store one or more program instructions;

[0131] A processor, configured to run one or more program instructions to execute a multi-channel signal transmission method based on big data;

[0132] Corresponding to the above-mentioned embodiments, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer storage medium contains one or more program instructions, and the one or more program instructions are used by a processor to execute a multi-channel signal transmission method based on big data.

[0133] The embodiments disclosed in the present invention provide a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned multi-channel signal transmission method based on big data.

[0134] In the embodiment of the present invention, the processor may be an integrated circuit chip having the signal processing capability. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0135] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or a mature storage medium in the art. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0136] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0137] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0138] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus DRAM (DRRAM).

[0139] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0140] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. Storage media can be any available media that can be accessed by general or special-purpose computers.

[0141] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions and improvements made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-channel signal transmission method based on big data, characterized in that: The method comprises: S10, capturing and preprocessing the signal data of each channel through the big data platform, and calculating the purity index of the signal of each channel; S20, inputting the signal purity index of each channel into the machine learning model respectively, predicting the future state value of each channel, and calculating the expected bandwidth utilization of each channel according to the future state value of each channel; S30, deriving an expected data transmission rate of each channel according to the expected bandwidth utilization of each channel; S40, calculating the transmission performance of each channel according to the expected data transmission rate of each channel and the stability of each channel; S50, acquiring signal data to be transmitted, determining transmission requirements, selecting several channels whose transmission performance meets the transmission requirements, and transmitting the signal data to be transmitted through the selected channels.

2. The multi-channel signal transmission method based on big data according to claim 1, characterized in that: The signal data of each channel is captured and preprocessed through the big data platform, and the signal purity index of each channel is calculated, including the following sub-steps: Use the collection function of the big data platform to collect signal data of each channel in real time; By denoising and normalizing the signal data collected by the big data platform, the signal data is normalized to a specific value range; The signal purity index of each channel is calculated by comprehensively considering the signal strength and frequency characteristics.

3. The multi-channel signal transmission method based on big data according to claim 1, characterized in that: The signal purity index of each channel is input into the machine learning model respectively to predict the future state value of each channel. The expected bandwidth utilization of each channel is calculated according to the future state value of each channel, including the following sub-steps: Select a support vector machine model, and input the preprocessed signal purity index of each channel into the selected machine learning model; The model predicts the state value of each channel in the future based on the input data; Based on the predicted future state value of each channel, the expected bandwidth utilization of each channel is calculated.

4. According to the multi-channel signal transmission method based on big data in claim 1, the expected data transmission rate of each channel is obtained according to the expected bandwidth utilization of each channel, comprising the following sub-steps: Determine a relationship formula between expected bandwidth utilization and expected data transmission rate, and substitute the expected bandwidth utilization of each channel into the relationship formula; The expected data transmission rate for each channel is calculated.

5. The multi-channel signal transmission method based on big data according to claim 1, characterized in that: According to the expected data transmission rate of each channel and the stability of each channel, the transmission performance of each channel is calculated, including the following sub-steps: Evaluate the stability of each channel by monitoring the channel's bit error rate, packet loss rate, and delay parameters; The transmission performance of each channel is calculated by combining the expected data transmission rate and stability evaluation results of each channel.

6. The multi-channel signal transmission method based on big data according to claim 1, characterized in that: Acquiring the signal data to be transmitted, determining the transmission requirements, and selecting several channels whose transmission performance meets the transmission requirements, including the following sub-steps: Determine the evaluation indicators and weights of transmission performance; Calculate the comprehensive transmission performance score of each channel based on the evaluation indicators and weights; Sort each channel according to the comprehensive transmission performance score; The number of channels to be selected is determined based on transmission requirements.

7. The multi-channel signal transmission method based on big data according to claim 6, characterized in that: Transmitting the signal data to be transmitted through the selected channel includes the following sub-steps: Determine the method of signal segmentation; Allocating the divided signal data to the selected multiple channels for parallel transmission; At the receiving end, the transmitted signal data is reassembled according to the segmentation order and rules; Check the integrity and correctness of the reassembled signal data.

8. A multi-channel signal transmission system based on big data, characterized in that: include: Data preprocessing module: Capture and preprocess the signal data of each channel through the big data platform, and calculate the purity index of each channel signal; Prediction module: Input the signal purity index of each channel into the machine learning model, predict the future state value of each channel, and calculate the expected bandwidth utilization of each channel based on the future state value of each channel; Data transmission rate calculation module: derives the expected data transmission rate of each channel according to the expected bandwidth utilization of each channel; Transmission performance evaluation module: calculates the transmission performance of each channel based on the expected data transmission rate of each channel and the stability of each channel; Signal transmission module: obtains the signal data to be transmitted, determines the transmission requirements, selects several channels whose transmission performance meets the transmission requirements, and transmits the signal data to be transmitted through the selected channels.

9. A computer storage medium, characterized in that: include: at least one memory and at least one processor; A memory for storing one or more program instructions; A processor, used to run one or more program instructions to execute a multi-channel signal transmission method based on big data as described in any one of claims 1-7.

Images