Marine ship transportation traffic prediction and evaluation system based on big data analysis

Abstract

The invention relates to the technical field of marine traffic management, in particular to a marine ship transportation traffic prediction and evaluation system based on big data analysis, which is used for solving the problems that the existing marine ship transportation traffic prediction and evaluation system is difficult to provide an accurate and comprehensive prediction and evaluation result, so that the marine traffic management efficiency is low, potential safety hazards exist and the cost is high. And the pressure of marine transportation management and operation is increased. The system performs preliminary screening on transportation routes according to a selection judgment coefficient, then performs data acquisition on predicted routes according to historical data, obtains a time prediction coefficient and a weather prediction coefficient based on a big data analysis technology, and obtains a smoothness prediction coefficient according to the time prediction coefficient and the weather prediction coefficient, and the smoothness prediction coefficient can comprehensively measure the smoothness degree of the transportation routes. According to the method, accurate prediction and comprehensive evaluation of marine ship transportation traffic conditions are realized, optimal scheduling suggestions and route planning can be provided for ships, and the safety and efficiency of marine ship transportation can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of maritime traffic management, and in particular to a maritime ship transport traffic prediction and evaluation system based on big data analysis. Background Art

[0002] With the development of the global economy, the importance of maritime transport has increased day by day, becoming an important pillar of global trade. However, this has also brought many challenges. The complexity and uncertainty of maritime transport, such as weather changes, route congestion and navigation restrictions, as well as the need for timely delivery of ships and cargo, have greatly affected transportation efficiency and safety. However, most of the existing maritime ship transportation traffic forecasting and evaluation systems have failed to make full use of a large amount of data for in-depth analysis and prediction, and it is difficult to provide accurate and comprehensive forecasting and evaluation results, resulting in low efficiency of maritime traffic management, certain safety hazards, and increased pressure on maritime transportation management and operations. Summary of the invention

[0003] In order to overcome the above-mentioned technical problems, the purpose of the present invention is to provide a marine ship transport traffic forecasting and evaluation system based on big data analysis, which solves the problem that the existing marine ship transport traffic forecasting and evaluation system is difficult to provide accurate and comprehensive forecasting and evaluation results, resulting in low efficiency of marine traffic management, potential safety hazards, and increased pressure on marine transport management and operations.

[0004] The purpose of the present invention can be achieved by the following technical solutions: A marine ship transportation traffic prediction and evaluation system based on big data analysis, comprising: The terminal operation module is used to obtain the selection judgment information of the analysis route o and send the selection judgment information to the data analysis module; wherein the selection judgment information includes the route length value LC and the travel time value XS; The data analysis module is used to obtain the selection judgment coefficient XPo according to the selection judgment information, and send the selection judgment coefficient XPo to the analysis and judgment module; it is also used to obtain the smoothness prediction coefficient LCu according to the time prediction coefficient SJu and the weather prediction coefficient TQu, and send the smoothness prediction coefficient LCu to the analysis and judgment module; The analysis and judgment module is used to obtain the predicted route u according to the selection judgment coefficient XPo, generate a time analysis instruction, and send the time analysis instruction to the time impact module; it is also used to classify the predicted route u as a congested route or a smooth route according to the smooth prediction coefficient LCu, and send the smooth route and the smooth prediction coefficient LCu to the prediction display module; The time impact module is used to obtain the ship driving information according to the historical data after receiving the time analysis instruction, and obtain the ship driving coefficient CX according to the ship driving information, and obtain the time prediction coefficient SJu according to the ship driving coefficient CX, and send the time prediction coefficient SJu to the data analysis module, and generate the weather analysis instruction at the same time, and send the weather analysis instruction to the weather impact module; wherein the ship driving information includes the average number of ships CS, the average ship driving speed CV and the average distance CJ between adjacent ships; The weather impact module is used to obtain weather deviation information after receiving the weather analysis instruction, obtain the weather deviation value PC according to the weather deviation information, obtain the weather prediction coefficient TQu according to the weather deviation value PC, and send the weather prediction coefficient TQu to the data analysis module; wherein the weather deviation information includes the temperature difference value WC, the humidity difference value SC, the speed difference value VC and the wind difference value FC; The prediction display module is used to display the prediction based on the smooth route and the smooth prediction coefficient LCu.

[0005] As a further solution of the present invention: the specific process of the terminal operation module obtaining the selection judgment information is as follows: The user inputs the starting point and the end point of the marine vessel transportation on the terminal device; the terminal device includes a computer, a tablet computer and a smart phone; Obtain all transportation routes between the starting point and the end point, and mark them as analysis routes o in sequence, where o=1, ..., n, where n is a positive integer, o is the number of any analysis route, and n is the total number of analysis routes; Obtain the route length of the analyzed route o and mark it as the route length value LC; Get the average travel time of all ships passing through the analysis route o within three days before the current time of the analysis route o, and mark it as the travel time value XS; The road length value LC and the travel time value XS are sent to the data analysis module.

[0006] As a further solution of the present invention: the specific process of the data analysis module obtaining the selection judgment coefficient XPo is as follows: Quantify the path length LC and the line time XS, extract the values ​​of the path length LC and the line time XS, and substitute them into the formula for calculation. The selection judgment coefficient XPo is obtained; wherein e is a mathematical constant, x1 and x2 are respectively preset proportional coefficients corresponding to the set road length value LC and the travel time value XS, x1 and x2 satisfy x1+x2=1, 0<x2<x1<1, and x1=0.58 and x2=0.42 are taken; The selection judgment coefficient XPo is sent to the analysis and judgment module.

[0007] As a further solution of the present invention: the specific process of the data analysis module obtaining the fluency prediction coefficient LCu is as follows: The time prediction coefficient SJu and weather prediction coefficient TQu are quantified, the values ​​of the time prediction coefficient SJu and weather prediction coefficient TQu are extracted, and substituted into the formula for calculation. Obtain the smooth prediction coefficient LCu; wherein y1 and y2 are the preset proportional coefficients corresponding to the set time prediction coefficient SJu and weather prediction coefficient TQu respectively, y1 and y2 satisfy y1+y2=1, 0<y2<y1<1, and y1=0.77, y2=0.23; The smooth prediction coefficient LCu is sent to the analysis and judgment module.

[0008] As a further solution of the present invention: the specific process of the analysis and judgment module obtaining the predicted route u is as follows: The selection judgment coefficient XPo is compared with the preset selection judgment threshold XPz, and the comparison results are as follows: If the selection judgment coefficient XPo≤selection judgment threshold XPz, the analysis route o corresponding to the selection judgment coefficient XPo is marked as a qualified route; All qualified routes are marked as predicted routes u in sequence, where u=1, ..., m, where m is a positive integer, u is the number of any predicted route, and m is the total number of predicted routes. At the same time, a time analysis instruction is generated and sent to the time impact module.

[0009] As a further solution of the present invention: the specific process of the analysis and judgment module classifying the predicted route u is as follows: The fluency prediction coefficient LCu is compared with the preset fluency prediction threshold LCz, and the comparison results are as follows: If the smooth prediction coefficient LCu is less than the smooth prediction threshold LCz, the predicted route u corresponding to the smooth prediction coefficient LCu is marked as a congested route; If the smooth prediction coefficient LCu ≥ the smooth prediction threshold LCz, the predicted route u corresponding to the smooth prediction coefficient LCu is marked as a smooth route, and the smooth route and the smooth prediction coefficient LCu are sent to the prediction display module.

[0010] As a further solution of the present invention: the specific process of the time impact module obtaining the time prediction coefficient SJu is as follows: After receiving the time analysis instruction, a day is divided into several prediction periods according to the preset time intervals, wherein the preset time intervals include 0.5h, 1h, 2h, 3h, 4h, 6h, 8h, 12h, and 24h; According to the forecast period to which the current moment belongs, the average number of ships CS, the average speed CV of ships, and the average distance CJ of adjacent ships traveling in the forecast route u in the same forecast period are obtained from historical data, and the average number of ships CS, the average speed CV of ships, and the average distance CJ of adjacent ships are quantified, and the values ​​of the average number of ships CS, the average speed CV of ships, and the average distance CJ of adjacent ships are extracted and substituted into the formula for calculation. According to the formula The ship travel coefficient CX is obtained; wherein c1, c2 and c3 are respectively the preset weight factors corresponding to the set average number of ships CS, the average ship travel speed CV and the average distance between adjacent ships CJ, and c1, c2 and c3 satisfy c1>c3>c2>1.46, and c1=3.18, c2=1.75, c3=2.41 are taken; Get the average value of the ship travel coefficient CX in the same forecast period of the first three days, the first ten days and the first thirty days, and mark them as the first ship travel value YX, the second ship travel value RX and the third ship travel value SX respectively, quantify the first ship travel value YX, the second ship travel value RX and the third ship travel value SX, extract the values ​​of the first ship travel value YX, the second ship travel value RX and the third ship travel value SX, and substitute them into the formula for calculation. According to the formula The time prediction coefficient SJu is obtained; wherein s1, s2 and s3 are preset proportional coefficients corresponding to the first ship value YX, the second ship value RX and the third ship value SX respectively, s1, s2 and s3 satisfy s1+s2+s3=1, 0<s3<s2<s1<1, and s1=0.42, s2=0.23, s3=0.35; The time prediction coefficient SJu is sent to the data analysis module, and a weather analysis instruction is generated at the same time, and the weather analysis instruction is sent to the weather impact module.

[0011] As a further solution of the present invention: the specific process of the weather impact module obtaining the weather prediction coefficient TQu is as follows: After receiving the weather analysis instruction, the difference between the ambient temperature of the current forecast route u and the preset standard temperature is obtained, and it is marked as the temperature difference value WC. The difference between the ambient humidity of the current forecast route u and the preset standard humidity is obtained, and it is marked as the humidity difference value SC. The difference between the average water flow rate of the current forecast route u and the preset standard water flow rate is obtained, and it is marked as the speed difference value VC. The difference between the average water surface wind speed of the current forecast route u and the preset standard water surface wind speed is obtained, and it is marked as the wind difference value FC. The temperature difference value WC, the humidity difference SC, the speed difference value VC and the wind difference value FC are quantified, and the values ​​of the temperature difference value WC, the humidity difference SC, the speed difference value VC and the wind difference value FC are extracted, and they are substituted into the formula for calculation. According to the formula Get the weather deviation value PC; wherein w1 and w2 are respectively the preset proportional coefficients corresponding to the set temperature difference value WC and the humidity difference value SC, w1 and w2 satisfy w1+w2=1, 0<w1<w2<1, w1=0.36, w2=0.64, w3 and w4 are respectively the preset proportional coefficients corresponding to the set speed difference value VC and the wind difference value FC, w3 and w4 satisfy w3+w4=1, 0<w3<w4<1, w3=0.45, w4=0.55; According to the forecast period to which the current moment belongs, the weather deviation value PC of the forecast route u in the same forecast period is obtained from the historical data, and it is marked as the historical weather deviation value PC1, and the difference between all the historical weather deviation values ​​PC1 and the weather deviation value PC is obtained respectively, and it is marked as the deviation deviation value PCp, and the forecast route u in the same forecast period in the historical data is sorted in the order of the deviation deviation value PCp from small to large, and the ship driving coefficient CX of the forecast route u in the same forecast period in the historical data at the first place is marked as the weather forecast coefficient TQu; The weather prediction coefficient TQu is sent to the data analysis module.

[0012] As a further solution of the present invention: the specific process of the prediction display module performing prediction display is as follows: All smooth routes are sorted and displayed in descending order according to the smooth prediction coefficient LCu, and the smooth routes are marked and displayed according to the value of the smooth prediction coefficient LCu.

[0013] Beneficial effects of the present invention: The present invention discloses a marine ship transportation traffic prediction and evaluation system based on big data analysis. First, the transportation route is preliminarily screened according to the selection judgment coefficient, and then the predicted route is data collected according to historical data, and the time prediction coefficient and the weather prediction coefficient are obtained based on the big data analysis technology, and the smoothness prediction coefficient is obtained according to the two. The smoothness prediction coefficient can comprehensively measure the smoothness of the transportation route, realize accurate prediction and comprehensive evaluation of the marine ship transportation traffic situation, and can provide the best scheduling suggestions and route planning for ships, reduce the sailing time and energy consumption of ships, improve the economic benefits of marine transportation, and even give early warning and take corresponding safety measures to reduce the risk of marine traffic accidents. It can effectively improve the safety and efficiency of marine ship transportation, provide intelligent decision-making support for marine traffic management, and is suitable for transportation conditions in different sea areas and different types of ships. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below in conjunction with the accompanying drawings.

[0015] Figure 1 This is a principle block diagram of a marine ship transportation traffic prediction and evaluation system based on big data analysis in the present invention; Figure 2 It is a flow chart of a working method of a marine ship transport traffic prediction and evaluation system based on big data analysis in the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1: Please refer to Figure 1 As shown, this embodiment is a marine ship transportation traffic prediction and evaluation system based on big data analysis, including the following modules: terminal operation module, data analysis module, analysis and judgment module, time impact module, weather impact module and prediction display module; The terminal operation module is used to obtain the selection judgment information of the analysis route o and send the selection judgment information to the data analysis module; wherein the selection judgment information includes the route length value LC and the travel time value XS; The data analysis module is used to obtain the selection judgment coefficient XPo according to the selection judgment information, and send the selection judgment coefficient XPo to the analysis and judgment module; it is also used to obtain the smooth prediction coefficient LCu according to the time prediction coefficient SJu and the weather prediction coefficient TQu, and send the smooth prediction coefficient LCu to the analysis and judgment module; The analysis and judgment module is used to obtain the predicted route u according to the selection judgment coefficient XPo, generate a time analysis instruction, and send the time analysis instruction to the time impact module; it is also used to classify the predicted route u as a congested route or a smooth route according to the smooth prediction coefficient LCu, and send the smooth route and the smooth prediction coefficient LCu to the prediction display module; The time impact module is used to obtain ship travel information according to historical data after receiving the time analysis instruction, wherein the ship travel information includes the average number of ships CS, the average ship travel speed CV and the average distance CJ of adjacent ships, and obtain the ship travel coefficient CX according to the ship travel information, and obtain the time prediction coefficient SJu according to the ship travel coefficient CX, and send the time prediction coefficient SJu to the data analysis module, and generate a weather analysis instruction at the same time, and send the weather analysis instruction to the weather impact module; The weather impact module is used to obtain weather deviation information after receiving the weather analysis instruction, wherein the weather deviation information includes a temperature difference value WC, a humidity difference value SC, a speed difference value VC, and a wind difference value FC, and obtain a weather deviation value PC according to the weather deviation information, and obtain a weather prediction coefficient TQu according to the weather deviation value PC, and send the weather prediction coefficient TQu to the data analysis module; The prediction display module is used to perform prediction display according to the smooth route and the smooth prediction coefficient LCu.

[0018] Example 2: Please refer to Figure 2 As shown, this embodiment is a working method of a marine ship transportation traffic prediction and evaluation system based on big data analysis, comprising the following steps: Step s1: the terminal operation module obtains the selection judgment information of the analysis route o, and sends the selection judgment information to the data analysis module; wherein the selection judgment information includes the route length value LC and the travel time value XS; Step s2: the data analysis module obtains the selection judgment coefficient XPo according to the selection judgment information, and sends the selection judgment coefficient XPo to the analysis and judgment module; Step s3: the analysis and judgment module obtains the predicted route u according to the selection judgment coefficient XPo, generates a time analysis instruction, and sends the time analysis instruction to the time impact module; Step s4: After receiving the time analysis instruction, the time impact module obtains the ship driving information according to the historical data, obtains the ship driving coefficient CX according to the ship driving information, obtains the time prediction coefficient SJu according to the ship driving coefficient CX, and sends the time prediction coefficient SJu to the data analysis module, and generates a weather analysis instruction at the same time, and sends the weather analysis instruction to the weather impact module; wherein the ship driving information includes the average number of ships CS, the average ship driving speed CV and the average distance CJ between adjacent ships; Step s5: After receiving the weather analysis instruction, the weather impact module obtains weather deviation information, obtains a weather deviation value PC according to the weather deviation information, obtains a weather prediction coefficient TQu according to the weather deviation value PC, and sends the weather prediction coefficient TQu to the data analysis module; wherein the weather deviation information includes a temperature difference value WC, a humidity difference value SC, a speed difference value VC, and a wind difference value FC; Step s6: the data analysis module obtains the smoothness prediction coefficient LCu according to the time prediction coefficient SJu and the weather prediction coefficient TQu, and sends the smoothness prediction coefficient LCu to the analysis and judgment module; Step s7: the analysis and judgment module classifies the predicted route u as a congested route or a smooth route according to the smooth prediction coefficient LCu, and sends the smooth route and the smooth prediction coefficient LCu to the prediction display module; Step s8: The prediction display module performs prediction display based on the smooth route and the smooth prediction coefficient LCu.

[0019] Embodiment 3: Based on any of the above embodiments, Embodiment 3 of the present invention is a terminal operation module, and the function of the terminal operation module is to obtain selection judgment information, wherein the selection judgment information includes a path length value LC and a travel time value XS. The specific process is as follows: The user inputs the starting point and the end point of the marine vessel transportation through the terminal operation module on the terminal device; wherein the terminal device includes a computer, a tablet computer and a smart phone; The terminal operation module obtains all the transportation routes between the starting point and the end point, and marks them as analysis routes o in sequence, where o=1, ..., n, n is a positive integer, o is the number of any analysis route, and n is the total number of analysis routes; The terminal operation module obtains the route length of the analysis route o and marks it as the route length value LC; The terminal operation module obtains the average travel time of all ships passing through the analysis route o within three days before the current time of the analysis route o, and marks it as the travel time value XS; The terminal operation module sends the road length value LC and the travel time value XS to the data analysis module.

[0020] Embodiment 4: Based on any of the above embodiments, Embodiment 4 of the present invention is a data analysis module, and the data analysis module has two functions; One of the functions is to obtain the selection judgment coefficient XPo. The specific process is as follows: The data analysis module quantifies the road length value LC and the travel time value XS, extracts the values ​​of the road length value LC and the travel time value XS, and substitutes them into the formula for calculation. The selection judgment coefficient XPo is obtained; wherein e is a mathematical constant, x1 and x2 are respectively preset proportional coefficients corresponding to the set road length value LC and the travel time value XS, x1 and x2 satisfy x1+x2=1, 0<x2<x1<1, and x1=0.58 and x2=0.42 are taken; The data analysis module sends the selection judgment coefficient XPo to the analysis and judgment module; The second function is to obtain the smooth prediction coefficient LCu. The specific process is as follows: The data analysis module quantifies the time prediction coefficient SJu and the weather prediction coefficient TQu, extracts the values ​​of the time prediction coefficient SJu and the weather prediction coefficient TQu, and substitutes them into the formula for calculation. Obtain the smooth prediction coefficient LCu; wherein y1 and y2 are the preset proportional coefficients corresponding to the set time prediction coefficient SJu and weather prediction coefficient TQu respectively, y1 and y2 satisfy y1+y2=1, 0<y2<y1<1, and y1=0.77, y2=0.23; The data analysis module sends the fluency prediction coefficient LCu to the analysis and judgment module.

[0021] Embodiment 5: Based on any of the above embodiments, Embodiment 5 of the present invention is an analysis and judgment module, which has two functions: One of the functions is to obtain the predicted route u. The specific process is as follows: The analysis and judgment module compares the selection judgment coefficient XPo with the preset selection judgment threshold XPz, and the comparison results are as follows: If the selection judgment coefficient XPo≤selection judgment threshold XPz, the analysis route o corresponding to the selection judgment coefficient XPo is marked as a qualified route; The analysis and judgment module marks all qualified routes as predicted routes u in sequence, where u=1, ..., m, where m is a positive integer, u is the number of any predicted route, and m is the total number of predicted routes. At the same time, a time analysis instruction is generated and sent to the time impact module. The second function is to classify the predicted route u. The specific process is as follows: The analysis and judgment module compares the fluency prediction coefficient LCu with the preset fluency prediction threshold LCz, and the comparison results are as follows: If the smooth prediction coefficient LCu is less than the smooth prediction threshold LCz, the predicted route u corresponding to the smooth prediction coefficient LCu is marked as a congested route; If the smooth prediction coefficient LCu ≥ the smooth prediction threshold LCz, the predicted route u corresponding to the smooth prediction coefficient LCu is marked as a smooth route, and the smooth route and the smooth prediction coefficient LCu are sent to the prediction display module.

[0022] Embodiment 6: Based on any of the above embodiments, Embodiment 6 of the present invention is a time impact module. The function of the time impact module is to obtain the time prediction coefficient SJu. The specific process is as follows: After receiving the time analysis instruction, the time impact module divides a day into several prediction periods according to the preset time intervals, wherein the preset time intervals include 0.5h, 1h, 2h, 3h, 4h, 6h, 8h, 12h, and 24h; The time impact module obtains the average number of ships CS, the average speed CV of ships, and the average distance CJ of adjacent ships traveling in the same prediction period u from historical data according to the prediction period to which the current moment belongs, and quantifies the average number of ships CS, the average speed CV of ships, and the average distance CJ of adjacent ships, extracts the values ​​of the average number of ships CS, the average speed CV of ships, and the average distance CJ of adjacent ships, and substitutes them into the formula for calculation. The ship travel coefficient CX is obtained; wherein c1, c2 and c3 are respectively the preset weight factors corresponding to the set average number of ships CS, the average ship travel speed CV and the average distance between adjacent ships CJ, and c1, c2 and c3 satisfy c1>c3>c2>1.46, and c1=3.18, c2=1.75, c3=2.41 are taken; The time impact module obtains the average value of the ship travel coefficient CX in the same forecast period of the first three days, the first ten days and the first thirty days, and marks them as the first ship travel value YX, the second ship travel value RX and the third ship travel value SX respectively, quantifies the first ship travel value YX, the second ship travel value RX and the third ship travel value SX, extracts the values ​​of the first ship travel value YX, the second ship travel value RX and the third ship travel value SX, and substitutes them into the formula for calculation. According to the formula The time prediction coefficient SJu is obtained; wherein s1, s2 and s3 are preset proportional coefficients corresponding to the first ship value YX, the second ship value RX and the third ship value SX respectively, s1, s2 and s3 satisfy s1+s2+s3=1, 0<s3<s2<s1<1, and s1=0.42, s2=0.23, s3=0.35; The time impact module sends the time prediction coefficient SJu to the data analysis module, generates a weather analysis instruction, and sends the weather analysis instruction to the weather impact module.

[0023] Embodiment 7: Based on any of the above embodiments, Embodiment 7 of the present invention is a weather influence module. The function of the weather influence module is to obtain the weather prediction coefficient TQu. The specific process is as follows: After receiving the weather analysis instruction, the weather impact module obtains the difference between the ambient temperature of the current prediction route u and the preset standard temperature, and marks it as the temperature difference value WC, obtains the difference between the ambient humidity of the current prediction route u and the preset standard humidity, and marks it as the humidity difference value SC, obtains the difference between the average water flow rate of the current prediction route u and the preset standard water flow rate, and marks it as the speed difference value VC, obtains the difference between the average water surface wind speed of the current prediction route u and the preset standard water surface wind speed, and marks it as the wind difference value FC, quantifies the temperature difference value WC, the humidity difference SC, the speed difference value VC and the wind difference value FC, extracts the values ​​of the temperature difference value WC, the humidity difference SC, the speed difference value VC and the wind difference value FC, and substitutes them into the formula for calculation. According to the formula Get the weather deviation value PC; wherein w1 and w2 are respectively the preset proportional coefficients corresponding to the set temperature difference value WC and the humidity difference value SC, w1 and w2 satisfy w1+w2=1, 0<w1<w2<1, w1=0.36, w2=0.64, w3 and w4 are respectively the preset proportional coefficients corresponding to the set speed difference value VC and the wind difference value FC, w3 and w4 satisfy w3+w4=1, 0<w3<w4<1, w3=0.45, w4=0.55; The weather impact module obtains the weather deviation value PC of the forecast route u in the same forecast period from the historical data according to the forecast period to which the current moment belongs, and marks it as the historical weather deviation value PCl, obtains the difference between all historical weather deviation values ​​PCl and the weather deviation value PC respectively, and marks it as the deviation deviation value PCp, sorts the forecast route u in the same forecast period in the historical data in the order of the deviation deviation value PCp from small to large, and marks the ship driving coefficient CX of the forecast route u in the same forecast period in the historical data at the first place as the weather forecast coefficient TQu; The weather impact module sends the weather prediction coefficient TQu to the data analysis module.

[0024] Embodiment 8: Based on any of the above embodiments, Embodiment 8 of the present invention is a prediction display module. The function of the prediction display module is to perform prediction display. The specific process is as follows: The prediction display module sorts and displays all the smooth routes in descending order according to the smooth prediction coefficient LCu, and marks and displays the smooth routes according to the value of the smooth prediction coefficient LCu.

[0025] Based on the above embodiments 1-8, the working principle of the present invention is as follows: The present invention provides a marine ship transportation traffic prediction and evaluation system based on big data analysis, which obtains selection judgment information of the analysis route through a terminal operation module, obtains a selection judgment coefficient according to the selection judgment information through a data analysis module, obtains a predicted route according to the selection judgment coefficient through an analysis and judgment module, obtains ship driving information according to historical data after receiving a time analysis instruction through a time influence module, obtains a ship driving coefficient according to the ship driving information, and obtains a time prediction coefficient according to the ship driving coefficient, obtains weather deviation information after receiving a weather analysis instruction through a weather influence module, obtains a weather deviation value according to the weather deviation information, and obtains a weather prediction coefficient according to the weather deviation value, obtains a smooth prediction coefficient according to the time prediction coefficient and the weather prediction coefficient through a data analysis module, and classifies the predicted route into a congested route or a smooth route according to the smooth prediction coefficient through an analysis and judgment module. line, and predicts and displays it according to the smooth route and smooth prediction coefficient through the prediction display module; the system first preliminarily screens the transportation route according to the selection judgment coefficient, and then collects data on the predicted route according to historical data, and obtains the time prediction coefficient and weather prediction coefficient based on big data analysis technology, and obtains the smooth prediction coefficient based on the two. The smooth prediction coefficient can comprehensively measure the smoothness of the transportation route, realize accurate prediction and comprehensive evaluation of the maritime ship transportation traffic situation, and can provide ships with the best scheduling suggestions and route planning, reduce the ship's sailing time and energy consumption, improve the economic benefits of maritime transportation, and even give early warning and take corresponding safety measures to reduce the risk of maritime traffic accidents. It can effectively improve the safety and efficiency of maritime ship transportation, provide intelligent decision-making support for maritime traffic management, and is suitable for transportation conditions in different sea areas and different types of ships.

[0026] It should be further explained that the above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by technical personnel in this field according to actual conditions.

[0027] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0028] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. A marine shipping traffic prediction and evaluation system based on big data analysis, characterized in that: include: The terminal operation module is used to obtain the selection judgment information of the analysis route o and send the selection judgment information to the data analysis module; wherein the selection judgment information includes the route length value LC and the travel time value XS; The data analysis module is used to obtain the selection judgment coefficient XPo according to the selection judgment information, and send the selection judgment coefficient XPo to the analysis and judgment module; it is also used to obtain the smoothness prediction coefficient LCu according to the time prediction coefficient SJu and the weather prediction coefficient TQu, and send the smoothness prediction coefficient LCu to the analysis and judgment module; The analysis and judgment module is used to obtain the predicted route u according to the selection judgment coefficient XPo, generate a time analysis instruction, and send the time analysis instruction to the time impact module; it is also used to classify the predicted route u as a congested route or a smooth route according to the smooth prediction coefficient LCu, and send the smooth route and the smooth prediction coefficient LCu to the prediction display module; The time impact module is used to obtain the ship driving information according to the historical data after receiving the time analysis instruction, and obtain the ship driving coefficient CX according to the ship driving information, and obtain the time prediction coefficient SJu according to the ship driving coefficient CX, and send the time prediction coefficient SJu to the data analysis module, and generate the weather analysis instruction at the same time, and send the weather analysis instruction to the weather impact module; wherein the ship driving information includes the average number of ships CS, the average ship driving speed CV and the average distance CJ between adjacent ships; The weather impact module is used to obtain weather deviation information after receiving the weather analysis instruction, obtain the weather deviation value PC according to the weather deviation information, obtain the weather prediction coefficient TQu according to the weather deviation value PC, and send the weather prediction coefficient TQu to the data analysis module; wherein the weather deviation information includes the temperature difference value WC, the humidity difference value SC, the speed difference value VC and the wind difference value FC; The prediction display module is used to display the prediction based on the smooth route and the smooth prediction coefficient LCu.

2. According to the big data analysis-based marine shipping traffic prediction and evaluation system of claim 1, it is characterized in that: The specific process of the terminal operation module obtaining the selection judgment information is as follows: The user inputs the starting point and the end point of the marine vessel transportation on the terminal device; Get all the transport routes between the starting point and the end point, and mark them as analysis route o in turn; get the route length of analysis route o, and mark it as the route length value LC; get the average travel time of all ships passing through analysis route o within three days before the current time of analysis route o, and mark it as the travel time value XS.

3. According to the big data analysis-based marine shipping traffic prediction and evaluation system of claim 1, it is characterized in that: The specific process of the data analysis module obtaining the selection judgment coefficient XPo is as follows: The road length value LC and the travel time value XS are quantified to obtain the selection judgment coefficient XPo, and the selection judgment coefficient XPo is sent to the analysis and judgment module.

4. According to the big data analysis-based marine shipping traffic prediction and evaluation system of claim 1, it is characterized in that: The specific process of the data analysis module obtaining the fluency prediction coefficient LCu is as follows: The time prediction coefficient SJu and the weather prediction coefficient TQu are quantified to obtain the smooth prediction coefficient LCu, and the smooth prediction coefficient LCu is sent to the analysis and judgment module.

5. The marine ship transportation traffic prediction and evaluation system based on big data analysis according to claim 1 is characterized in that: The specific process of the analysis and judgment module obtaining the predicted route u is as follows: The selection judgment coefficient XPo is compared with the preset selection judgment threshold XPz, and the comparison results are as follows: If the selection judgment coefficient XPo≤selection judgment threshold XPz, the analysis route o corresponding to the selection judgment coefficient XPo is marked as a qualified route, and all qualified routes are marked as predicted routes u in turn.

6. The marine ship transportation traffic prediction and evaluation system based on big data analysis according to claim 1 is characterized in that: The specific process of the analysis and judgment module classifying the predicted route u is as follows: The fluency prediction coefficient LCu is compared with the preset fluency prediction threshold LCz, and the comparison results are as follows: If the smooth prediction coefficient LCu is less than the smooth prediction threshold LCz, the predicted route u corresponding to the smooth prediction coefficient LCu is marked as a congested route; if the smooth prediction coefficient LCu is greater than or equal to the smooth prediction threshold LCz, the predicted route u corresponding to the smooth prediction coefficient LCu is marked as a smooth route.

7. The marine ship transportation traffic prediction and evaluation system based on big data analysis according to claim 1 is characterized in that: The specific process of the time impact module obtaining the time prediction coefficient SJu is as follows: After receiving the time analysis instruction, a day is divided into several forecast periods according to the preset time intervals; According to the prediction period to which the current moment belongs, the average number of ships CS, the average speed of ships CV and the average distance between adjacent ships CJ of ships traveling in the prediction route u in the same prediction period are obtained from historical data, and the average number of ships CS, the average speed of ships CV and the average distance between adjacent ships CJ are quantified to obtain the ship travel coefficient CX; Get the average value of the ship travel coefficient CX in the same prediction period of the previous three days, the previous ten days and the previous thirty days, and mark them as the first ship travel value YX, the second ship travel value RX and the third ship travel value SX respectively, quantize the first ship travel value YX, the second ship travel value RX and the third ship travel value SX to obtain the time prediction coefficient SJu.

8. The marine ship transportation traffic prediction and evaluation system based on big data analysis according to claim 1 is characterized in that: The specific process of the weather impact module obtaining the weather prediction coefficient TQu is as follows: After receiving the weather analysis instruction, the difference between the ambient temperature of the current prediction route u and the preset standard temperature is obtained, and it is marked as the temperature difference value WC; the difference between the ambient humidity of the current prediction route u and the preset standard humidity is obtained, and it is marked as the humidity difference value SC; the difference between the average water flow rate of the current prediction route u and the preset standard water flow rate is obtained, and it is marked as the speed difference value VC; the difference between the average water surface wind speed of the current prediction route u and the preset standard water surface wind speed is obtained, and it is marked as the wind difference value FC; the temperature difference value WC, the humidity difference SC, the speed difference value VC and the wind difference value FC are quantified to obtain the weather deviation value PC; According to the prediction period to which the current moment belongs, the weather deviation value PC of the prediction route u in the same prediction period is obtained from the historical data, and it is marked as the historical weather deviation value PCl. The differences between all historical weather deviation values ​​PCl and the weather deviation value PC are obtained respectively, and they are marked as deviation deviation values ​​PCp. The prediction route u in the same prediction period in the historical data is sorted in ascending order according to the deviation deviation value PCp, and the ship driving coefficient CX of the prediction route u in the same prediction period in the historical data that ranks first is marked as the weather prediction coefficient TQu.

9. The marine ship transportation traffic prediction and evaluation system based on big data analysis according to claim 1 is characterized in that: The specific process of the prediction display module performing prediction display is as follows: All smooth routes are sorted and displayed in descending order according to the smooth prediction coefficient LCu, and the smooth routes are marked and displayed according to the value of the smooth prediction coefficient LCu.

Images