Engineering test detection data efficient transmission method based on 5G technology

Abstract

The invention relates to the technical field of digital information transmission, in particular to an engineering test detection data efficient transmission method based on the 5G technology, and the method comprises the steps: obtaining engineering test detection data of a target road section of a target road; performing noise analysis on the actual road surface flatness of the target road section, and determining the overall noise of the actual road surface flatness of the target road section; adjusting an initial learning rate of an optimizer of the long short-term memory network model according to the overall noise to obtain a target long short-term memory network model; predicting the predicted pavement flatness of the target road section by using the target long-short-term memory network model; determining a Huffman tree based on the actual pavement flatness and the predicted pavement flatness of the target road section; and compressing the actual pavement flatness of the target road section by using the Huffman tree to obtain compressed data, and transmitting the compressed data based on the 5G technology. According to the invention, the compression effect of data compression is optimized, and the data transmission efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital information transmission, and particularly to an efficient transmission method for engineering test and detection data based on 5G technology. Background Art

[0002] In traffic engineering, the engineering test and detection data of roads is crucial for the safety, comfort, and durability of roads. The engineering test and detection data of roads can include pavement evenness. In order to ensure that the monitoring system can instantaneously integrate and analyze a large amount of pavement evenness data, optimize resource allocation, and improve the accuracy and efficiency of road infrastructure management, it is necessary to compress the pavement evenness detected in traffic engineering and then transmit it to the database.

[0003] In some scenarios, the Huffman coding algorithm is often used to compress the pavement evenness, and then the 5th-Generation Mobile Communication Technology (5G) is used for transmission. Due to factors such as vehicle jolts caused by tire wear of vehicles and soil accumulation layers, the detected pavement evenness may have excessive noise. When using the Huffman coding algorithm to compress the pavement evenness with data distortion, the coding length of the compressed coded data is too long, and the compression effect is poor. Therefore, in order to improve the compression effect of the Huffman coding algorithm for data compression, a Long Short-Term Memory (LSTM) model is used to predict the pavement evenness using the historical pavement evenness sequence, and then the difference between the pavement evenness predicted by the LSTM model and the actual pavement evenness is used to optimize the Huffman coding algorithm, thereby improving the compression effect. However, when using the LSTM model to predict the pavement evenness, not all the historical pavement evenness at its time step is necessarily the real pavement evenness, and there may also be noise data. If there is too much noise data at the time step, it will cause the predicted value predicted by the LSTM model to be inaccurate, the optimization effect of the Huffman coding algorithm to be poor, and further lead to a poor compression effect of the Huffman coding algorithm for data compression, a too long coding length of the compressed coded data, a high bandwidth requirement and data transmission time in the 5G transmission process, and a low data transmission efficiency. Summary of the Invention

[0004] In order to solve the technical problems of poor compression effect of the Huffman coding algorithm for data compression and low data transmission efficiency, the purpose of the present invention is to provide an efficient transmission method for engineering test and detection data based on 5G technology, and the specific technical solution adopted is as follows:

[0005] An embodiment of the present invention provides an efficient transmission method for engineering test and detection data based on 5G technology, including: obtaining engineering test and detection data of a target section of a target road, where the engineering test and detection data includes the actual road surface flatness of the target section, and the actual road surface flatness is determined by the height values between multiple measurement points of the target section and the measurement device; performing noise analysis on the actual road surface flatness of the target section to determine the overall noise of the actual road surface flatness of the target section, where the overall noise characterizes the possibility that the actual road surface flatness of the target section belongs to noise; adjusting the initial learning rate of the optimizer of the long short-term memory network model according to the overall noise of the actual road surface flatness of the target section to obtain the target long short-term memory network model; using the target long short-term memory network model to predict the predicted road surface flatness of the target section; determining a Huffman tree based on the actual road surface flatness and the predicted road surface flatness of the target section; compressing the actual road surface flatness of the target section using the Huffman tree to obtain compressed data, and transmitting the compressed data based on 5G technology.

[0006] Optionally, performing noise analysis on the actual road surface flatness of the target section to determine the overall noise of the actual road surface flatness of the target section includes: obtaining the height values between multiple measurement points of the target section and the measurement device; determining the desirability of the actual road surface flatness of the target section according to the difference between adjacent height values, where the adjacent height values are the height values at adjacent acquisition times in time series, and the desirability characterizes the continuity of the actual road surface flatness of the target section; obtaining the first actual road surface flatness and the first desirability of the first actual road surface flatness in the first preset number of days, and the second actual road surface flatness and the second desirability of the second actual road surface flatness in the second preset number of days, where the first preset number of days is at least one day before the time corresponding to the actual road surface flatness of the target section, and the second preset number of days is at least one day after the time corresponding to the actual road surface flatness of the target section; determining the probability that the actual road surface flatness of the target section belongs to a mutation point according to the desirability of the actual road surface flatness of the target section, the first actual road surface flatness, the first desirability, the second actual road surface flatness, and the second desirability; determining the one-dimensional noise of the actual road surface flatness of the target section according to the regression model of the actual road surface flatness of the target section, where the regression model is constructed based on the probability that the actual road surface flatness of the target section belongs to a mutation point, the change rate parameter, and the flatness upper limit value; determining the overall trend similarity between the actual road surface flatness of the target section and the actual road surface flatness of the adjacent sections according to the regression model of the actual road surface flatness of the target section and the regression models of the adjacent sections on both sides of the target section; determining the overall noise of the actual road surface flatness of the target section according to the one-dimensional noise of the adjacent sections on both sides of the target section, the one-dimensional noise of the target section, and the overall trend similarity.

[0007] Optionally, before determining the one-dimensional noise of the actual road surface flatness of the target road section according to the regression model of the actual road surface flatness of the target road section, the method further includes: obtaining the historical actual road surface flatness of multiple road sections in the third preset number of days; determining the probability that each historical actual road surface flatness belongs to a mutation point and the desirability of each historical actual road surface flatness; determining a regression model according to the last day in the third preset number of days, the change rate parameter, the flatness upper limit value, the probability that each historical actual road surface flatness belongs to a mutation point, and the number of days in the third preset number of days where each historical actual road surface flatness is located; determining a correction error function according to the desirability of each historical actual road surface flatness, the regression model, and each historical actual road surface flatness; taking the minimization of the correction error function as the goal, and solving the change rate parameter and the flatness upper limit value of the regression model by the gradient descent method.

[0008] Optionally, determining the overall trend similarity between the actual road surface flatness of the target road section and the actual road surface flatness of the adjacent road sections according to the regression model of the actual road surface flatness of the target road section and the regression models of the adjacent road sections on both sides of the target road section includes: obtaining the first probability that each actual road surface flatness of the target road section belongs to a mutation point in the fourth preset number of days, and the second probability that the actual road surface flatness of the adjacent road sections on both sides of the target road section belongs to a mutation point; determining the first regression model of each actual road surface flatness of the target road section according to each first probability, and determining the second regression model of each actual road surface flatness of the adjacent road sections according to each second probability; using the first regression model and the second regression model to determine the overall trend similarity.

[0009] Optionally, determining the desirability of the actual road surface flatness of the target road section according to the difference between each adjacent height value includes: determining the absolute value of the difference between each adjacent height value and the average value of each difference; respectively calculating the square of the difference between the absolute value of each difference and the average value to obtain a squared value, and adding up each squared value to obtain a first added value; using an exponential function to perform a negative correlation process on the first added value to obtain the desirability of the actual road surface flatness of the target road section.

[0010] Optionally, determining the probability that the actual road surface flatness of the target road section belongs to a mutation point according to the desirability of the actual road surface flatness of the target road section, the first actual road surface flatness, the first desirability, the second actual road surface flatness, and the second desirability includes: calculating a second added value of the first product of each first actual road surface flatness and the first desirability in the first preset number of days, and a third added value of the second product of each second actual road surface flatness and the second desirability in the second preset number of days; calculating the third product of the absolute value of the difference between the second added value and the third added value and the reciprocal of the desirability of the actual road surface flatness; using a maximum-minimum normalization function to normalize the third product to obtain the probability that the actual road surface flatness of the target road section belongs to a mutation point.

[0011] Optionally, determining the one-dimensional noise of the actual road surface flatness of the target section according to the regression model of the actual road surface flatness of the target section includes: determining the target calculation formula in the regression model according to the probability that the actual road surface flatness of the target section belongs to the mutation point; using the target calculation formula to determine the predicted road surface flatness of the target section;

[0012] Determining the absolute value of the difference between the predicted road surface flatness and the actual road surface flatness of the target section as the one-dimensional noise of the actual road surface flatness of the target section.

[0013] Optionally, determining the overall noise of the actual road surface flatness of the target section according to the one-dimensional noise of the adjacent sections on both sides of the target section, the one-dimensional noise of the target section, and the overall trend similarity includes: calculating the average one-dimensional noise of the one-dimensional noise of the adjacent sections on both sides of the target section; multiplying the average one-dimensional noise after negative correlation processing by the exponential function with the one-dimensional noise of the target section to obtain a fourth product; determining the product of the fourth product and the overall trend similarity as the overall noise of the actual road surface flatness of the target section.

[0014] Optionally, adjusting the initial learning rate of the optimizer of the long short-term memory network model according to the overall noise of the actual road surface flatness of the target section to obtain the target long short-term memory network model includes: obtaining the initial learning rate of the optimizer of the long short-term memory network model and the overall noise of the actual road surface flatness of the target section at multiple time steps; respectively calculating the difference between the preset value and the actual road surface flatness of the target section, and calculating the fourth superposition value of the ratio of the difference between the actual road surface flatness and the number of actual road surface flatness of the target section at the time step; taking the absolute value of the fourth superposition value; determining the product of the absolute value and the initial learning rate as the optimized learning rate; determining the target long short-term memory network model according to the optimized learning rate.

[0015] Optionally, determining the Huffman tree based on the actual road surface flatness and the predicted road surface flatness of the target section includes: determining the normalized difference of the actual road surface flatness of the target section according to the predicted road surface flatness and the actual road surface flatness of the target section; determining the forwardness of the actual road surface flatness of the target section as a node based on the normalized difference and the number of occurrences of the actual road surface flatness of the target section; determining the Huffman tree using the forwardness of the actual road surface flatness of the target section as a node.

[0016] The present invention has the following beneficial effects: First, obtain the engineering test and detection data of the target section of the target road. The engineering test and detection data includes the actual road surface flatness of the target section, and the actual road surface flatness is determined by the height values between multiple measurement points of the target section and the measuring device. Then, perform noise analysis on the actual road surface flatness of the target section to determine the overall noise of the actual road surface flatness of the target section. The overall noise characterizes the possibility that the actual road surface flatness of the target section belongs to noise. Secondly, adjust the initial learning rate of the optimizer of the long short-term memory network model according to the overall noise of the actual road surface flatness of the target section to obtain the target long short-term memory network model. Then, use the target long short-term memory network model to predict the predicted road surface flatness of the target section. And determine the Huffman tree based on the actual road surface flatness and the predicted road surface flatness of the target section. Finally, use the Huffman tree to compress the actual road surface flatness to obtain compressed data, and transmit the compressed data based on 5G technology.

[0017] In this way, the present invention adjusts the initial learning rate of the optimizer of the long short-term memory network model through the overall noise of the actual road surface flatness of the target road obtained by measurement, improves the accuracy of the predicted value of the LSTM model, reduces the deviation between the predicted value and the actual road surface flatness, and improves the compression effect of the Huffman coding algorithm based on the more accurate predicted road surface flatness predicted by the LSTM model. The compressed coded data can be transmitted by 5G with a shorter coding length, thereby reducing the bandwidth requirement and data transmission time during the 5G transmission process and improving the efficiency of data transmission. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a flowchart of an efficient transmission method for engineering test and detection data based on 5G technology provided by an embodiment of the present invention.

[0020] Figure 2 It is a schematic diagram of the module composition of an efficient transmission system for engineering test and detection data based on 5G technology provided by an embodiment of the present invention.

[0021] Figure 3 It is a schematic diagram of the structure of an efficient transmission system for engineering test and detection data based on 5G technology to implement an embodiment of the present invention. Detailed Embodiments

[0022] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a method for efficiently transmitting engineering test and detection data based on 5G technology according to the present invention, including its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0024] The following specifically describes the specific solution of a method for efficiently transmitting engineering test and detection data based on 5G technology provided by the present invention in conjunction with the accompanying drawings.

[0025] Embodiment 1:

[0026] Please refer to Figure 1 , which shows a flowchart of a method for efficiently transmitting engineering test and detection data based on 5G technology provided by an embodiment of the present invention, including:

[0027] S101, obtaining engineering test and detection data of a target section of a target road.

[0028] Among them, the engineering test and detection data includes the actual road surface flatness of the target section. The actual road surface flatness is determined by the height values between multiple measurement points of the target section and the measurement device.

[0029] Specifically, the target road refers to the road that needs to be subjected to flatness detection. The target section refers to a section of the target road. The actual road surface flatness of the target section can be measured by a measurement device, and the measurement device includes a laser rangefinder and a road flatness detection vehicle. The laser rangefinder can be installed in the center of the body of the road flatness detection vehicle, and it is used to measure the distance between the center of the body and the ground of the target section. There are multiple measurement points in the target section, and the variance of the height values between these measurement points and the center of the body is used to represent the actual road surface flatness of the target section. For example, when the front of the road flatness detection vehicle reaches the boundary of the target section, the laser rangefinder starts to collect the distance between the center of the body and the ground where the measurement point is located, and this distance is the height value between the measurement point and the measurement device. At a frequency of x frames per second, the measurement ends when the rear of the road flatness detection vehicle leaves the target section. A total of n height values of the center of the body from the ground are obtained, and the variance of these n height values is used to represent the actual road surface flatness of the target section.

[0030] Further, for the target road section, two more road sections are respectively set at a preset distance on both sides thereof as adjacent road sections, and the actual road surface flatness on these two adjacent road sections is obtained by using a measuring device, so as to facilitate the analysis of the trend similarity of the road surface flatness between road sections in subsequent embodiments. The preset distance can be determined according to actual conditions. In the embodiments of the present invention, the value is 1 km. The two sides of the target road section refer to the two road sections adjacent to the left and right sides of the target road section along the advancing direction of the measuring device. Of course, according to actual conditions, the two sides of the target road section may also be other situations, which are not limited in the embodiments of the present invention.

[0031] S102, perform noise analysis on the actual road surface flatness of the target road section to determine the overall noise of the actual road surface flatness of the target road section.

[0032] Among them, the overall noise characterizes the possibility that the actual road surface flatness of the target road section belongs to noise.

[0033] Specifically, the overall noise characterizes the possibility that the actual road surface flatness belongs to noise, that is, the authenticity of the actual road surface flatness. The higher the overall noise, the greater the possibility that the actual road surface flatness belongs to noise, and the lower the authenticity of the actual road surface flatness. When determining the overall noise of the actual road surface flatness, first, it is necessary to determine the noise of the actual road surface flatness of each day of each target road section. First, analyze from a single data point. For each target road section, since each target road section presents a Logistic function model (regression model) with time variation, it is necessary to minimize the error sum between the predicted value and the actual value for function fitting. However, if the actual road surface flatness is unacceptable data and has a large contribution rate to the error sum minimization function, the fitting result will become extremely inaccurate. Therefore, first, calculate the acceptability of each actual road surface flatness through the characteristics of the continuous and relatively uniform change of the target road section. Secondly, since the mutation point in the initial parameters of the Logistic function model is unknown, determine the mutation point through the left and right fluctuation conditions under the acceptability of the actual road surface flatness, determine the optimal function for fitting through the mutation point, error, and function, and determine the one-dimensional noise of the actual road surface flatness by using the difference between the actual road surface flatness and the function; then analyze from the adjacent sides of the current target road section, and determine the overall noise of the actual road surface flatness of the target road section through the overall trend similarity between the actual road surface flatness of the target road section and the actual road surface flatness of the adjacent road sections.

[0034] Further, when determining the overall noise of the actual road surface flatness, as an optional embodiment of the present invention, first obtain the height values from multiple measurement points on the target road section to the measurement device. Then determine the desirability of the actual road surface flatness of the target road section according to the differences between adjacent height values. The adjacent height values are the height values at adjacent acquisition times in time series, and the desirability characterizes the continuity of the actual road surface flatness of the target road section. Then obtain the first actual road surface flatness and the first desirability of the first actual road surface flatness for the first preset number of days, and the second actual road surface flatness and the second desirability of the second actual road surface flatness for the second preset number of days. The first preset number of days is at least one day before the time corresponding to the actual road surface flatness of the target road section, and the second preset number of days is at least one day after the time corresponding to the actual road surface flatness of the target road section. Secondly, according to the desirability of the actual road surface flatness of the target road section, the first actual road surface flatness, the first desirability, the second actual road surface flatness and the second desirability, determine the probability that the actual road surface flatness of the target road section belongs to a mutation point. Then determine the one-dimensional noise of the actual road surface flatness of the target road section according to the regression model of the actual road surface flatness of the target road section. The regression model is constructed based on the probability that the actual road surface flatness of the target road section belongs to a mutation point, the change rate parameter and the flatness upper limit value. Then, according to the regression model of the actual road surface flatness of the target road section and the regression models of the adjacent road sections on both sides of the target road section, determine the overall trend similarity between the actual road surface flatness of the target road section and the actual road surface flatness of the adjacent road sections. Finally, determine the overall noise of the actual road surface flatness of the target road section according to the one-dimensional noise of the adjacent road sections on both sides of the target road section, the one-dimensional noise of the target road section and the overall trend similarity.

[0035] Specifically, the desirability characterizes the continuity of the actual road surface flatness of the target road section. Since the road surface is usually composed of continuous materials (such as soil, concrete, paving materials, etc.), and these materials are continuous in physical and mechanical properties, therefore, the change of the actual road surface flatness of the road should also be continuous. The higher the continuity of the actual road surface flatness of the target road section, the higher the desirability. When determining the desirability of the actual road surface flatness of the target road section, first determine the differences between adjacent height values and the average value of each difference; then calculate the squares of the differences between each difference and the average value respectively to obtain squared values, and superimpose the squared values to obtain a first superimposed value; finally, perform a negative correlation process on the first superimposed value using an exponential function to obtain the desirability of the actual road surface flatness of the target road section.

[0036] Among them, the desirability can be expressed by the following formula:

[0037]

[0038] In the above formula, P QIndicates the desirability of the actual road surface flatness Q of the target road section. exp represents the exponential function with base e, which is used for performing negative correlation processing. n represents that when obtaining the actual road surface flatness Q of the target road section, a total of n height values between the center of the vehicle body and the ground where the measurement points of the target road section are located are collected using the measuring device. Represents the (i + 1)-th height value between the center of the vehicle body and the ground where the measurement point of the target road section is located when obtaining the actual road surface flatness Q of the target road section using the measuring device. Represents the i-th height value between the center of the vehicle body and the ground where the measurement point of the target road section is located when obtaining the actual road surface flatness Q of the target road section using the measuring device. Represents the absolute value of the difference between the (i + 1)-th and the i-th height values between the center of the vehicle body and the ground where the measurement points of the target road section are located. u represents the average value of the differences between adjacent two of the n height values collected using the measuring device when obtaining the actual road surface flatness Q of the target road section.

[0039] Furthermore, since the road surface is usually composed of continuous materials (such as soil, concrete, paving materials, etc.), and these materials are continuous in physical and mechanical properties, the change in road surface flatness should also be continuous. Analyzing the acquisition process when obtaining the actual road surface flatness Q of the target road section, it can be seen that because it is a process of continuously collecting the height values of each measurement point, the differences between adjacent height values between the center of the vehicle body and the ground where the measurement points of the target road section are located are also similar. Therefore, through the change of the variance between adjacent height values to determine the similarity of the differences between adjacent height values. The larger the variance, the smaller the similarity, and P Q is smaller.

[0040] Furthermore, after determining the desirability of the actual road surface flatness of the target road section, then determine the probability that the actual road surface flatness of the target road section belongs to a mutation point. When determining the probability that the actual road surface flatness of the target road section belongs to a mutation point, first obtain the first actual road surface flatness and the first desirability of the first actual road surface flatness for the first preset number of days, and the second actual road surface flatness and the second desirability of the second actual road surface flatness for the second preset number of days. Then calculate the second superimposed value of the first product of each first actual road surface flatness and the first desirability in the first preset number of days, and the third superimposed value of the second product of each second actual road surface flatness and the second desirability in the second preset number of days; then calculate the third product of the absolute value of the difference between the second superimposed value and the third superimposed value and the reciprocal of the desirability of the actual road surface flatness; finally, normalize the third product using the maximum-minimum normalization function to obtain the probability that the actual road surface flatness of the target road section belongs to a mutation point.

[0041] Specifically, the first actual road surface flatness and the second actual road surface flatness can be obtained in the manner described in step S101 of the above embodiment. The first desirability and the second desirability can be calculated according to the desirability calculation formula described in the above embodiment of the present invention. The values of the first preset number of days and the second preset number of days can be determined according to the actual situation, and their values can be the same or different. In the embodiment of the present invention, both the first preset number of days and the second preset number of days are set to 7 days.

[0042] Further, the probability that the actual road surface flatness of the target section belongs to a mutation point can be calculated by the following formula:

[0043]

[0044] In the above formula, T Q represents the probability that the actual road surface flatness Q of the target section belongs to a mutation point. F represents the maximum-minimum normalization function, which is used to perform normalization. v represents that a total of v days are selected forward and backward from the time corresponding to the actual road surface flatness Q of the target section. P Q ′ i represents the first desirability of the first actual road surface flatness on the i-th day selected forward from the time corresponding to the actual road surface flatness Q of the target section. Z ′ Qi represents the first actual road surface flatness on the i-th day selected forward from the time corresponding to the actual road surface flatness Q of the target section. P Q ″ i represents the second desirability of the second actual road surface flatness on the i-th day selected backward from the time corresponding to the actual road surface flatness Q of the target section. Z ′ Q ′ i represents the second actual road surface flatness on the i-th day selected backward from the time corresponding to the actual road surface flatness Q of the target section. P Q represents the desirability of the actual road surface flatness Q of the target section.

[0045] Further, for the mutation point of the regression model to be constructed (such as the Logistic function model), first, the desirability of the actual road surface flatness Q of the target section is a prerequisite. If the road surface flatness within the preset number of days before the time corresponding to the actual road surface flatness Q of the target section differs significantly from the road surface flatness within the preset number of days after the time corresponding to the actual road surface flatness Q of the target section, and the smaller the actual road surface flatness Q of the target section, that is, the larger the reciprocal of the actual road surface flatness Q of the target section, the greater the probability that the actual road surface flatness Q of the target section belongs to a mutation point.

[0046] Further, the regression model can be a Logistic function model, which is used to represent the change of road surface flatness over time. Before applying the regression model to determine the one-dimensional noise of the actual road surface flatness, it is necessary to construct the regression model. When constructing the regression model, first obtain the historical actual road surface flatness of multiple road sections in the third preset number of days; then determine the probability that each historical actual road surface flatness belongs to a mutation point and the desirability of each historical actual road surface flatness; then determine the regression model according to the last day in the third preset number of days, the change rate parameter, the flatness upper limit value, the probability that each historical actual road surface flatness belongs to a mutation point, and the number of days in which each historical actual road surface flatness is located in the third preset number of days; secondly, determine the correction error function according to the desirability of each historical actual road surface flatness, the regression model, and each historical actual road surface flatness; finally, with the goal of minimizing the correction error function, solve the change rate parameter and the flatness upper limit value of the regression model by the gradient descent method.

[0047] Specifically, the third preset number of days can be determined according to the actual situation, and the embodiments of the present invention do not limit this here. The probability that the historical actual road surface flatness belongs to a mutation point and the desirability of each historical actual road surface flatness can both be calculated by the calculation formulas described in the above embodiments of the present invention. In the embodiments of the present invention, taking the regression model as a Logistic function model as an example, the regression model is represented by the following formula:

[0048]

[0049] In the above formula, Z(t) represents the Logistic function model, L represents the flatness upper limit value, k represents the change rate parameter, which is used to control the steepness of the sharp decline of the road surface flatness. t A represents the number of days in which the historical actual road surface flatness A is located in the third preset number of days. t represents the third preset number of days. t 1 represents the last day in the third preset number of days when the historical actual road surface flatness A is obtained. T A represents the probability that the historical actual road surface flatness A belongs to a mutation point. e represents the natural constant.

[0050] Further, the correction error function can be represented by the following formula:

[0051]

[0052] In the above formula, E represents the correction error function. m represents that a total of m days of historical actual road surface flatness are obtained. P iIt represents the desirability of the historical actual road surface smoothness on the i-th day in m. Z(i) represents the predicted road surface smoothness obtained by substituting the probability that the historical actual road surface smoothness on the i-th day belongs to a mutation point into the above Logistic function model. Z i It represents the historical actual road surface smoothness on the i-th day.

[0053] Furthermore, since the minimum value of the error between the predicted road surface smoothness and the historical actual road surface smoothness is used to determine the parameters L and k of the Logistic function model, the embodiments of the present invention make the contribution of the historical actual road surface smoothness with lower desirability to the error smaller, and the contribution of the historical actual road surface smoothness with higher desirability to the error larger, so as to make the parameters L and k of the Logistic function model obtained most accurately. Through the gradient descent method, the parameters L and k of the Logistic function model can be obtained, and thus the regression model construction is completed.

[0054] Furthermore, after the regression model is constructed, the one-dimensional noise of the actual road surface smoothness of the target section can be determined by using the regression model. When determining the one-dimensional noise of the actual road surface smoothness of the target section, as an optional embodiment of the present invention, the target calculation formula in the regression model is determined according to the probability that the actual road surface smoothness of the target section belongs to a mutation point; the predicted road surface smoothness of the target section is determined by using the target calculation formula; and the absolute value of the difference between the predicted road surface smoothness and the actual road surface smoothness of the target section is determined as the one-dimensional noise of the actual road surface smoothness of the target section.

[0055] Specifically, as recorded in the above embodiments of the present invention, the regression model includes two parts. The first part is when the probability of the mutation point is greater than 0.7, the formula is used to calculate the predicted road surface smoothness of the target section. The second part is when the probability of the mutation point is not greater than 0.7, the formula is used to calculate the predicted road surface smoothness of the target section. Therefore, the probability that the actual road surface smoothness of the target section belongs to a mutation point is compared with 0.7 to determine the target calculation formula. After determining the target calculation formula, the predicted road surface smoothness of the target section is calculated according to the formula.

[0056] Furthermore, the one-dimensional noise of the actual road surface smoothness of the target section can be expressed by the following formula:

[0057] W Q =|Z(Q)-Z Q |;

[0058] In the above formula, W Q represents the one-dimensional noise of the actual road surface smoothness Q of the target section. Z(Q) represents the predicted road surface smoothness of the target section. Z QRepresents the actual road surface smoothness Q of the target road section.

[0059] Furthermore, since the actual road surface smoothness of different road sections of the target road all show the pattern demonstrated by the regression model in terms of time sequence, the more it does not conform to the pattern shown by the regression model, that is, the larger |Z(Q) - Z Q | is, the greater the one-dimensional noise of the actual road surface smoothness of the target road section.

[0060] Furthermore, because similar materials and construction methods were used in the construction of the adjacent road sections adjacent to the target road section, and the traffic flow and vehicle types borne by the adjacent road sections are similar, their wear degrees and deformation trends will also be similar, so their overall trends should be similar. The overall trend similarity can be determined by the integral error of the regression model. Therefore, when determining the overall trend similarity, as an optional embodiment of the present invention, first obtain the first probability that each actual road surface smoothness of the target road section on the fourth preset number of days belongs to a mutation point, and the second probability that the actual road surface smoothness of the adjacent road sections on both sides of the target road section belongs to a mutation point; then determine the first regression model of each actual road surface smoothness of the target road section according to each first probability, and determine the second regression model of each actual road surface smoothness of the adjacent road sections according to each second probability; finally, use the first regression model and the second regression model to determine the overall trend similarity.

[0061] Specifically, the fourth preset number of days can be a continuous number of days. The first probability that each actual road surface smoothness of the target road section on the fourth preset number of days belongs to a mutation point and the second probability that each actual road surface smoothness of the adjacent road sections on the fourth preset number of days belongs to a mutation point can be calculated by the formula described in the above embodiments of the present invention. After obtaining each first probability and second probability, compare them with 0.7 to obtain the first regression model and the second regression model. The overall trend similarity can be calculated using the following formula:

[0062]

[0063] In the above formula, S represents the overall trend similarity between the actual road surface smoothness of the target road section and the actual road surface smoothness of the adjacent road sections. exp represents the exponential function with e as the base, which is used to perform a negative correlation process on t 0 represents the initial day when a total of the fourth preset number of days is observed. t 1 represents the end day when a total of the fourth preset number of days is observed. Z ′(t) represents the Logistic function model (the second regression model) of the actual road surface evenness of the adjacent road section adjacent to one side of the target road section. Z(t) represents the Logistic function model (the first regression model) of the actual road surface evenness of the target road section. Z″(t) represents the Logistic function model (the second regression model) of the actual road surface evenness of the adjacent road section adjacent to the other side of the target road section. represents the integral of |Z ′ (t) - Z(t)| from t 0 to t 1 on. represents the integral of |Z″(t) - Z(t)| from t 0 to t 1 on. Z ′ (t) - Z(t) represents the difference between the second regression model of the actual road surface evenness of the adjacent road section adjacent to one side of the target road section and the first regression model of the actual road surface evenness of the target road section, that is, the error between the predicted road surface evenness of the adjacent road section adjacent to one side of the target road section and the predicted road surface evenness of the target road section. Z″(t) - Z(t) represents the difference between the second regression model of the actual road surface evenness of the adjacent road section adjacent to the other side of the target road section and the first regression model of the actual road surface evenness of the target road section, that is, the error between the predicted road surface evenness of the adjacent road section adjacent to the other side of the target road section and the predicted road surface evenness of the target road section.

[0064] Furthermore, since the probability that the target road section and the adjacent road sections on its two sides have a mutation point through the actual road surface evenness can both obtain a Logistic function model that conforms to itself, therefore, the overall trend similarity can be determined based on the coincidence degree of the Logistic function models of the target road section and the adjacent road sections on its two sides. In the above formula, it is manifested that the smaller the area enclosed by the integral curve of the target road section and the integral curve of the adjacent road section, the better. The smaller the area, the higher the corresponding S, that is, the higher the overall trend similarity between the actual road surface evenness of the target road section and the actual road surface evenness of the adjacent road section.

[0065] Furthermore, after obtaining the overall trend similarity and the one-dimensional noise of the target road section, the overall noise of the actual road surface evenness of the target road section can be determined in combination with the one-dimensional noise of the adjacent road sections. As an optional embodiment of the present invention, when determining the overall noise of the actual road surface evenness of the target road section, first calculate the average one-dimensional noise of the one-dimensional noises of the adjacent road sections on both sides of the target road section; then perform a negative correlation process on the average one-dimensional noise using an exponential function and multiply it by the one-dimensional noise of the target road section to obtain a fourth product; finally, determine the product of the fourth product and the overall trend similarity as the overall noise of the actual road surface evenness of the target road section.

[0066] Specifically, the overall noise of the actual road surface flatness of the target section can be expressed by the following formula:

[0067]

[0068] In the above formula, M Q represents the overall noise of the actual road surface flatness Q of the target section. exp represents the exponential function with base e, which is used to perform negative correlation processing on . W Q represents the one-dimensional noise of the actual road surface flatness Q of the target section. W ′ Q represents the one-dimensional noise of the actual road surface flatness of the adjacent section adjacent to one side of the target section on the same day. W ′ Q ′ represents the one-dimensional noise of the actual road surface flatness of the adjacent section adjacent to the other side of the target section on the same day. S represents the overall trend similarity between the actual road surface flatness of the target section and that of the adjacent section.

[0069] S103. Adjust the initial learning rate of the optimizer of the long short-term memory network model according to the overall noise of the actual road surface flatness of the target section to obtain the target long short-term memory network model.

[0070] Specifically, if there is a lot of noise data in the time step of the long short-term memory network model, it will have a great impact on the prediction result of the long short-term memory network model. Therefore, the learning rate of the optimizer in the long short-term memory network model needs to be adjusted through the overall noise of all the actual road surface flatness in the time step to weaken the sensitivity of the long short-term memory network model to noise and make the prediction result of the long short-term memory network model more accurate. Among them, the optimizer of the long short-term memory network model can be the Adam optimizer.

[0071] Furthermore, when adjusting the initial learning rate of the optimizer of the long short-term memory network model, as an optional embodiment of the present invention, first obtain the initial learning rate of the optimizer of the long short-term memory network model and the overall noise of multiple actual road surface flatness of the target section in the time step; then calculate the difference between the preset value and each actual road surface flatness of the target section respectively, and calculate the fourth superposition value of the ratio of each difference to the number of actual road surface flatness of the target section in the time step; then take the absolute value of the fourth superposition value; secondly, determine the product of the absolute value and the initial learning rate as the optimized learning rate; finally, determine the target long short-term memory network model according to the optimized learning rate.

[0072] Specifically, the multiple actual road surface evenness of the target road section can be the historical actual road surface evenness of the target road section collected continuously for h days. The preset value can be taken according to the actual situation, and the value in the embodiment of the present invention is 1. The optimizer can determine its type according to the actual scenario, and the Adam optimizer is adopted in the embodiment of the present invention. Further, the optimized learning rate can be expressed by the following formula:

[0073]

[0074] In the above formula, represents the optimized learning rate of the Adam optimizer for all historical actual road surface evenness at the time step. h represents that there are h historical actual road surface evenness of the target road section at the time step. M i represents the overall noise of the historical actual road surface evenness on the i-th day at the time step. represents the average non-noise rate of all historical actual road surface evenness at the time step. X represents the initial learning rate of the Adam optimizer for all historical actual road surface evenness at the time step.

[0075] Further, in the long short-term memory network model, a large amount of noise in the data will reduce the accuracy of the prediction result. At this time, using the average non-noise rate of the historical actual road surface evenness at the time step to optimize the learning rate of the Adam optimizer can reduce the fluctuation of the long short-term memory network model in the error caused by noise, can greatly reduce the overreaction to the noise data, make each weight update more robust, help the long short-term memory network model to adjust smoothly during the training process, reduce the sensitivity to noise, and thus improve the stability and prediction accuracy of the long short-term memory network model.

[0076] In addition, the historical actual road surface evenness of other road sections of the target road can also be used to optimize the learning rate of the optimizer of the long short-term memory network model, or the historical actual road surface evenness of different road sections of other roads can be used to optimize the learning rate of the optimizer of the long short-term memory network model. The embodiment of the present invention does not make any limitation here.

[0077] S104, use the target long short-term memory network model to predict the predicted road surface evenness of the target road section.

[0078] Specifically, the learning rate of the Adam optimizer in the target long short-term memory network model has been optimized. Therefore, using the target long short-term memory network model to predict the predicted road surface evenness of the target road section has higher accuracy. When predicting the predicted road surface evenness of the target road section, the historical actual road surface evenness of at least one day of the target road section can be input into the target long short-term memory network model, and the target long short-term memory network model is used to predict the road surface evenness of the target road section to obtain the predicted road surface evenness.

[0079] S105, determine the Huffman tree based on the actual road surface flatness and the predicted road surface flatness of the target road section.

[0080] Specifically, since the road surface flatness has the characteristics of time series, for the road surface flatness, the above optimized target long short-term memory network model is used to predict the road surface flatness of the target road section, and the predicted road surface flatness corresponding to the actual road surface flatness of the target road is obtained. If the difference between the predicted road surface flatness of the target long short-term memory network model and the actual road surface flatness is large, it may be due to vehicle bumps caused by tire wear, etc., and deviations caused by occasional soil accumulation, etc. The possibility of such data being noise data is relatively large, and it is not the data that needs to be focused on. Therefore, the actual road surface flatness and the predicted road surface flatness of the target road section are used to optimize the Huffman tree. The optimized Huffman tree is used to compress the actual road surface flatness with a large difference from the predicted road surface flatness, so that the Huffman code for compressing this part using the Huffman tree is relatively long (low forwardness), while the optimized Huffman tree is used to compress the actual road surface flatness with a small difference between the predicted value and the actual value, and its Huffman code is relatively short, that is, high forwardness, so that the actual road surface flatness with a small difference between the predicted value and the actual value can be better compressed and better protected.

[0081] Further, when determining the Huffman tree, as an optional embodiment of the present invention, first determine the normalized difference of the actual road surface flatness of the target road section according to the predicted road surface flatness and the actual road surface flatness of the target road section; then determine the forwardness of the nodes formed by the actual road surface flatness of the target road section based on the normalized difference and the number of occurrences of the actual road surface flatness of the target road section; finally, determine the Huffman tree using the forwardness of the nodes formed by the actual road surface flatness of the target road section.

[0082] Specifically, the normalized difference of the actual road surface flatness of the target road section can be calculated by the following formula:

[0083]

[0084] In the above formula, C represents the normalized difference between the predicted value and the actual value of each actual road surface flatness. Y represents the predicted value of each actual road surface flatness, that is, the predicted road surface flatness. Z represents the actual value of each actual road surface flatness. |Y - Z| represents the difference between the predicted value and the actual value. C m[x represents the maximum value of the differences between all predicted values and actual values of the target road section. C min represents the minimum value of the differences between all predicted values and actual values of the target road section.

[0085] Further, the forwardness of the nodes formed by the actual road surface flatness can be expressed by the following formula:

[0086]

[0087] In the above formula, G represents the forwardness of each actual road surface flatness composition node. exp represents the exponential function with base e, which is used to perform negative correlation processing on. a represents the number of times the actual road surface flatness with the same value appears. C i represents the normalized difference between the predicted value and the actual value when the actual road surface flatness with the same value appears for the i-th time. Among them, the higher the forwardness of the actual road surface flatness composition node, the higher the importance of the actual road surface flatness. When the optimized Huffman tree compresses the actual road surface flatness with high forwardness, the Huffman code is shorter, resulting in better compression. And the lower the forwardness of the actual road surface flatness composition node, the lower the importance of the actual road surface flatness, which can be removed as noise data, thus retaining more important data

[0088] Through the above embodiments, the forwardness of the actual road surface flatness composition node has been determined. Next, the actual road surface flatness with forwardness lower than the threshold can be removed as noise data, and the remaining actual road surface flatness with forwardness higher than the threshold can be used to construct a Huffman tree based on the method of constructing a Huffman tree in the prior art, that is, continuously merge the nodes corresponding to the forwardness of the two smallest nodes to form a new node, and then merge it with the node corresponding to the forwardness of the remaining smallest node to construct a Huffman tree based on each actual road surface flatness.

[0089] S106, use the Huffman tree to compress the actual road surface flatness of the target section to obtain compressed data, and transmit the compressed data based on 5G technology.

[0090] Specifically, using the Huffman tree to compress the actual road surface flatness of the target section can be to replace each character in the actual road surface flatness with the corresponding Huffman code to obtain compressed data. The principle of using the Huffman tree to compress data can be referred to the prior art, and it will not be elaborated in this embodiment of the present invention.

[0091] In the embodiment of the present invention, the overall noise of the actual road surface flatness of the target road obtained by measurement is used to adjust the initial learning rate of the optimizer of the long short-term memory network model, which improves the accuracy of the prediction value of the LSTM model, reduces the deviation between the prediction value and the actual road surface flatness, and improves the Huffman coding algorithm compression effect based on the more accurate predicted road surface flatness predicted by the LSTM model. The compressed coded data can be transmitted by 5G with a shorter coding length, thereby reducing the bandwidth requirement and data transmission time during the 5G transmission process and improving the data transmission efficiency. In addition, since the volume of the compressed data is reduced, the probability of encountering errors during the 5G transmission process is also reduced, improving the stability, security, and reliability during the data transmission process.

[0092] Embodiment 2:

[0093] Corresponding to the method for efficient transmission of engineering test and detection data based on 5G technology provided in the above embodiment, based on the same technical concept, the embodiment of the present invention also provides a system for efficient transmission of engineering test and detection data based on 5G technology, as Figure 2 shown in Figure 2 is a schematic diagram of the module composition of a system for efficient transmission of engineering test and detection data based on 5G technology provided in the embodiment of the present invention. The system 200 for efficient transmission of engineering test and detection data based on 5G technology includes: an acquisition module 201 for acquiring engineering test and detection data of the target section of the target road, where the engineering test and detection data includes the actual road surface flatness of the target section, and the actual road surface flatness is determined by the height values between multiple measurement points of the target section and the measurement device; an analysis module 202 for performing noise analysis on the actual road surface flatness of the target section to determine the overall noise of the actual road surface flatness of the target section, where the overall noise characterizes the possibility that the actual road surface flatness of the target section belongs to noise; an adjustment module 203 for adjusting the initial learning rate of the optimizer of the long short-term memory network model according to the overall noise of the actual road surface flatness of the target section to obtain a target long short-term memory network model; a prediction module 204 for using the target long short-term memory network model to predict the predicted road surface flatness of the target section; a determination module 205 for determining a Huffman tree based on the actual road surface flatness and the predicted road surface flatness of the target section; and a compression module 206 for compressing the actual road surface flatness of the target section using the Huffman tree to obtain compressed data and transmitting the compressed data based on 5G technology.

[0094] In an embodiment of the present invention, the initial learning rate of the optimizer of the long short-term memory network model is adjusted according to the overall noise of the actual road surface flatness of the target road obtained by measurement, improving the accuracy of the predicted value of the LSTM model, reducing the deviation between the predicted value and the actual road surface flatness. Based on the more accurate predicted road surface flatness predicted by the LSTM model, the compression effect of the Huffman coding algorithm is improved, and the encoded data obtained by compression can be transmitted via 5G with a shorter coding length, thereby reducing the bandwidth requirement and data transmission time during 5G transmission, and improving the efficiency of data transmission. In addition, since the volume of the compressed data is reduced, the probability of encountering errors during 5G transmission is also decreased, improving the stability, security, and reliability during data transmission.

[0095] Optionally, the analysis module 202 is further configured to obtain the height values between multiple measurement points of the target road section and the measurement device; determine the desirability of the actual road surface flatness of the target road section according to the differences between adjacent height values, where the adjacent height values are the height values at adjacent acquisition times in time series, and the desirability characterizes the continuity of the actual road surface flatness of the target road section; obtain the first actual road surface flatness and the first desirability of the first actual road surface flatness for the first preset number of days, and the second actual road surface flatness and the second desirability of the second actual road surface flatness for the second preset number of days, where the first preset number of days is at least one day before the time corresponding to the actual road surface flatness of the target road section, and the second preset number of days is at least one day after the time corresponding to the actual road surface flatness of the target road section; determine the probability that the actual road surface flatness of the target road section belongs to a mutation point according to the desirability of the actual road surface flatness of the target road section, the first actual road surface flatness, the first desirability, the second actual road surface flatness, and the second desirability; determine the one-dimensional noise of the actual road surface flatness of the target road section according to the regression model of the actual road surface flatness of the target road section, where the regression model is constructed based on the probability that the actual road surface flatness of the target road section belongs to a mutation point, the change rate parameter, and the flatness upper limit value; determine the overall trend similarity between the actual road surface flatness of the target road section and the actual road surface flatness of the adjacent road sections according to the regression model of the actual road surface flatness of the target road section and the regression models of the adjacent road sections on both sides of the target road section; determine the overall noise of the actual road surface flatness of the target road section according to the one-dimensional noise of the adjacent road sections on both sides of the target road section, the one-dimensional noise of the target road section, and the overall trend similarity.

[0096] Optionally, the determination module 205 is further configured to obtain the historical actual road surface flatness of multiple road sections for the third preset number of days; determine the probability that each historical actual road surface flatness belongs to a mutation point and the desirability of each historical actual road surface flatness;

[0097] Determine a regression model based on the last day of the third preset number of days, the change rate parameter, the upper limit value of flatness, the probability that each historical actual road surface flatness belongs to a mutation point, and the number of days in the third preset number of days when each historical actual road surface flatness is located; determine a correction error function based on the desirability of each historical actual road surface flatness, the regression model, and each historical actual road surface flatness; with the goal of minimizing the correction error function, solve the change rate parameter and the upper limit value of flatness of the regression model through the gradient descent method.

[0098] Optionally, the determination module 205 is further configured to obtain the first probability that each actual road surface flatness of the target road section in the fourth preset number of days belongs to a mutation point, and the second probability that the actual road surface flatness of the adjacent road sections on both sides of the target road section belongs to a mutation point; determine the first regression model of each actual road surface flatness of the target road section according to each first probability, and determine the second regression model of each actual road surface flatness of the adjacent road sections according to each second probability; use the first regression model and the second regression model to determine the overall trend similarity.

[0099] Optionally, the determination module 205 is further configured to determine the absolute value of the difference between each adjacent height value, and the average value of each difference; calculate the square of the difference between the absolute value of each difference and the average value respectively to obtain a squared value, and superimpose each squared value to obtain a first superimposed value; perform a negative correlation process on the first superimposed value using an exponential function to obtain the desirability of the actual road surface flatness of the target road section.

[0100] Optionally, the determination module 205 is further configured to calculate a second superimposed value of the first product of each first actual road surface flatness and the first desirability in the first preset number of days, and a third superimposed value of the second product of each second actual road surface flatness and the second desirability in the second preset number of days; calculate the third product of the absolute value of the difference between the second superimposed value and the third superimposed value and the reciprocal of the desirability of the actual road surface flatness; normalize the third product using the maximum-minimum normalization function to obtain the probability that the actual road surface flatness of the target road section belongs to a mutation point.

[0101] Optionally, the determination module 205 is further configured to determine the target calculation formula in the regression model according to the probability that the actual road surface flatness of the target road section belongs to a mutation point; use the target calculation formula to determine the predicted road surface flatness of the target road section; determine the absolute value of the difference between the predicted road surface flatness and the actual road surface flatness of the target road section as the single-dimensional noise of the actual road surface flatness of the target road section.

[0102] Optionally, the determination module 205 is further configured to calculate the average one-dimensional noise of adjacent road sections on both sides of the target road section; multiply the average one-dimensional noise after performing negative correlation processing on the average one-dimensional noise using an exponential function by the one-dimensional noise of the target road section to obtain a fourth product; determine that the product of the fourth product and the overall trend similarity is the overall noise of the actual road surface flatness of the target road section.

[0103] Optionally, the adjustment module 203 is further configured to obtain the initial learning rate of the optimizer of the long short-term memory network model and the overall noise of the actual road surface flatness of the target road section at multiple time steps; calculate the difference between the preset value and each actual road surface flatness of the target road section respectively, and calculate the fourth superposition value of the ratio of the difference between each actual road surface flatness and the number of actual road surface flatness of the target road section at the time step; take the absolute value of the fourth superposition value; determine that the product of the absolute value and the initial learning rate is the optimized learning rate; determine the target long short-term memory network model according to the optimized learning rate.

[0104] Optionally, the determination module 205 is further configured to determine the normalized difference of the actual road surface flatness of the target road section according to the predicted road surface flatness and the actual road surface flatness of the target road section; determine the forwardness of the nodes formed by the actual road surface flatness of the target road section based on the normalized difference and the number of occurrences of the actual road surface flatness of the target road section; determine the Huffman tree using the forwardness of the nodes formed by the actual road surface flatness of the target road section.

[0105] Embodiment III:

[0106] Corresponding to the method for efficiently transmitting engineering test detection data based on 5G technology provided in the above embodiment, based on the same technical concept, the embodiment of the present invention also provides another engineering test detection data efficient transmission system based on 5G technology. The engineering test detection data efficient transmission system based on 5G technology is used to execute the method for efficiently transmitting engineering test detection data based on 5G technology described above. Figure 3 For the structural schematic diagram of an engineering test detection data efficient transmission system based on 5G technology according to an embodiment of the present invention, as Figure 3 shown. The engineering test detection data efficient transmission system based on 5G technology may vary greatly due to configuration or performance differences, and may include one or more processors 301 and a memory 302. The memory 302 is used to store computer programs that can run on the processor. The processor 301 is used to execute the programs stored in the memory 302 to implement each step in the above Figure 1 method embodiments. Among them, the memory 302 can be a short-term storage or a persistent storage. The application programs stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions for the engineering test detection data efficient transmission system based on 5G technology.

[0107] Furthermore, the processor 301 can be configured to communicate with the memory 302 and execute a series of computer-executable instructions in the memory 302 on the high-efficiency transmission system for engineering test detection data based on 5G technology. The high-efficiency transmission system for engineering test detection data based on 5G technology may further include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0108] Specifically, in this embodiment, the high-efficiency transmission system for engineering test detection data based on 5G technology includes a processor, a communication interface, a memory, and a communication bus; wherein, the processor, the communication interface, and the memory complete mutual communication through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored on the memory to implement each step in the method embodiments above Figure 1 and has the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described in detail here.

[0109] It should be noted that the high-efficiency transmission system for engineering test detection data based on 5G technology provided by the embodiments of the present invention and the high-efficiency transmission method for engineering test detection data based on 5G technology provided by the embodiments of the present invention are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned high-efficiency transmission method for engineering test detection data based on 5G technology and has the same or similar beneficial effects. The repeated parts will not be described again.

[0110] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A method for efficient transmission of engineering test data based on 5G technology, characterized in that: The method for efficiently transmitting engineering test detection data based on 5G technology includes: Acquire engineering test detection data of a target section of a target road, wherein the engineering test detection data includes actual road surface smoothness of the target section, wherein the actual road surface smoothness is determined by height values ​​between a plurality of measurement points of the target section and a measurement device; Performing a noise analysis on the actual road surface smoothness of the target road section to determine the overall noise of the actual road surface smoothness of the target road section, wherein the overall noise indicates the possibility that the actual road surface smoothness of the target road section is noise; Adjusting the initial learning rate of the optimizer of the long short-term memory network model according to the overall noisiness of the actual road surface smoothness of the target road section to obtain a target long short-term memory network model; Predicting the predicted road surface smoothness of the target road section using the target long short-term memory network model; Determining a Huffman tree based on the actual road surface roughness of the target road section and the predicted road surface roughness; The Huffman tree is used to compress the actual road surface flatness of the target road section to obtain compressed data, and the compressed data is transmitted based on 5G technology.

2. According to claim 1, the method for efficient transmission of engineering test detection data based on 5G technology is characterized in that: The performing noise analysis on the actual road surface smoothness of the target road section to determine the overall noise of the actual road surface smoothness of the target road section comprises: Acquire the height values ​​between a plurality of measuring points of the target road section and the measuring device; Determining the desirability of the actual road surface smoothness of the target road section according to the difference between each adjacent height value, wherein the adjacent height values ​​are height values ​​at adjacent collection times in time sequence, and the desirability represents the continuity of the actual road surface smoothness of the target road section; Obtaining a first actual road surface flatness and a first desirability of the first actual road surface flatness on a first preset day, and a second actual road surface flatness and a second desirability of the second actual road surface flatness on a second preset day, wherein the first preset day is at least one day before a time corresponding to the actual road surface flatness of the target road section, and the second preset day is at least one day after a time corresponding to the actual road surface flatness of the target road section; Determining a probability that the actual road surface smoothness of the target road section belongs to a mutation point according to the desirability of the actual road surface smoothness of the target road section, the first actual road surface smoothness, the first desirability, the second actual road surface smoothness, and the second desirability; Determining the unidimensional noise of the actual road surface smoothness of the target road section according to a regression model of the actual road surface smoothness of the target road section, wherein the regression model is constructed based on the probability that the actual road surface smoothness of the target road section belongs to a mutation point, a change rate parameter, and an upper limit value of the smoothness; Determine the overall trend similarity between the actual road surface smoothness of the target road section and the actual road surface smoothness of the adjacent road sections based on the regression model of the actual road surface smoothness of the target road section and the regression models of the adjacent road sections on both sides of the target road section; The overall noisiness of the actual road surface smoothness of the target road section is determined according to the one-dimensional noisiness of the adjacent road sections on both sides of the target road section, the one-dimensional noisiness of the target road section and the overall trend similarity.

3. The method for efficiently transmitting engineering test data based on 5G technology according to claim 2 is characterized in that: Before determining the unidimensional noise of the actual road surface smoothness of the target road section according to the regression model of the actual road surface smoothness of the target road section, the method further includes: Obtaining historical actual road surface smoothness of multiple road sections on a third preset number of days; Determining the probability that each of the historical actual road surface smoothnesses belongs to a mutation point and the desirability of each of the historical actual road surface smoothnesses; Determine the regression model according to the last day of the third preset number of days, the change rate parameter, the upper limit value of the flatness, the probability that each of the historical actual road surface flatnesses belongs to a mutation point, and the day on which each of the historical actual road surface flatnesses falls in the third preset number of days; Determining a correction error function according to the desirability of each of the historical actual road surface smoothnesses, the regression model, and each of the historical actual road surface smoothnesses; With the minimization of the modified error function as the goal, the change rate parameter and the upper limit value of the flatness of the regression model are solved by the gradient descent method.

4. The method for efficiently transmitting engineering test data based on 5G technology according to claim 2 is characterized in that: Determining the overall trend similarity between the actual road surface smoothness of the target road section and the actual road surface smoothness of the adjacent road sections based on the regression model of the actual road surface smoothness of the target road section and the regression models of the adjacent road sections on both sides of the target road section includes: Obtaining a first probability that each of the actual road surface roughness of the target road section on the fourth preset day belongs to a mutation point, and a second probability that the actual road surface roughness of adjacent road sections on both sides of the target road section belongs to a mutation point; Determine a first regression model of each actual road surface roughness of each target road section according to each first probability, and determine a second regression model of each actual road surface roughness of each adjacent road section according to each second probability; The overall trend similarity is determined using the first regression model and the second regression model.

5. The method for efficient transmission of engineering test detection data based on 5G technology according to claim 2 is characterized in that: The desirability of determining the actual road surface flatness of the target road section according to the difference between each adjacent height value includes: Determine the absolute value of the difference between each of the adjacent height values, and the average value of each of the differences; respectively calculating the square of the difference between the absolute value of each difference and the average value to obtain a square value, and superimposing the square values ​​to obtain a first superimposed value; The first superposition value is negatively correlated with the first superposition value by using an exponential function to obtain the desirability of the actual road surface flatness of the target road section.

6. The method for efficiently transmitting engineering test data based on 5G technology according to claim 2 is characterized in that: Determining the probability that the actual road surface smoothness of the target road section belongs to a mutation point according to the desirability of the actual road surface smoothness of the target road section, the first actual road surface smoothness, the first desirability, the second actual road surface smoothness, and the second desirability includes: Calculating a second superposition value of a first product of the first actual road surface roughness and the first desirability for each of the first preset days, and a third superposition value of a second product of the second actual road surface roughness and the second desirability for each of the second preset days; calculating a third product of the absolute value of the difference between the second superimposed value and the third superimposed value and the inverse of the desirability of the actual road surface flatness; The third product is normalized using a maximum-minimum normalization function to obtain a probability that the actual road surface flatness of the target road section belongs to a mutation point.

7. The method for efficient transmission of engineering test detection data based on 5G technology according to claim 2 is characterized in that: The step of determining the single-dimensional noise of the actual road surface roughness of the target road section according to the regression model of the actual road surface roughness of the target road section comprises: Determining the target calculation formula in the regression model according to the probability that the actual road surface flatness of the target road section belongs to a mutation point; Determining the predicted road surface smoothness of the target road section using the target calculation formula; The absolute value of the difference between the predicted road surface roughness and the actual road surface roughness of the target road section is determined as the unidimensional noise of the actual road surface roughness of the target road section.

8. The method for efficient transmission of engineering test detection data based on 5G technology according to claim 2 is characterized in that: The method of determining the overall noise of the actual road surface flatness of the target road section according to the one-dimensional noise of the adjacent road sections on both sides of the target road section, the one-dimensional noise of the target road section and the overall trend similarity includes: Calculating the average unidimensional noise of the unidimensional noises of the adjacent road sections on both sides of the target road section; Performing negative correlation processing on the average one-dimensional noise by using an exponential function and then multiplying the result by the one-dimensional noise of the target road section to obtain a fourth product; The product of the fourth product and the overall trend similarity is determined as the overall noise of the actual road surface smoothness of the target road section.

9. The method for efficient transmission of engineering test detection data based on 5G technology according to any one of claims 1 to 8, characterized in that: The initial learning rate of the optimizer of the long short-term memory network model is adjusted according to the overall noise of the actual road surface flatness of the target road section to obtain the target long short-term memory network model, including: Obtaining the initial learning rate of the optimizer of the long short-term memory network model and the overall noise of multiple actual road surface roughness of the target road section at the time step; Calculating the difference between the preset value and each actual road surface roughness of the target road section respectively, and calculating a fourth superposition value of the ratio of the difference between each actual road surface roughness to the number of actual road surface roughness of the target road section at the time step; taking the absolute value of the fourth superposition value; Determine the product of the absolute value and the initial learning rate as the optimized learning rate after optimization; The target long short-term memory network model is determined according to the optimized learning rate.

10. The method for efficient transmission of engineering test data based on 5G technology according to any one of claims 1 to 8, characterized in that: Determining the Huffman tree based on the actual road surface roughness of the target road section and the predicted road surface roughness comprises: Determining a normalized difference in actual road surface smoothness of the target road section according to the predicted road surface smoothness and the actual road surface smoothness of the target road section; Determining the forwardness of the actual road surface roughness constituent node of the target road segment based on the normalized difference and the number of occurrences of the actual road surface roughness of the target road segment; The Huffman tree is determined by using the actual road surface flatness of the target road section to form the forwardness of the node.

Images