Global shipping data real-time anomaly monitoring method and system

Abstract

The invention relates to the field of deep mining and analysis of ship AIS (Automatic Identification System) data, and provides a method and a system for real-time anomaly monitoring of global shipping data. Shipping indexes are generated according to data such as cargo types, loads, ship departure places and destinations of shipping ships, abnormal operation data are automatically screened out through abnormal rule setting, and decision analysis support is provided for users in time; meanwhile, the abnormal frequency of a single shipping index in a plurality of continuous periods or a specified range can be analyzed, and the problem that the shipping index can only analyze and display a single index is solved; according to the method, all the abnormal indexes are concentrated on the map to be displayed, the display content comprises the fluctuation range, the period length and the abnormal concentration area of the abnormal data indexes, and a user is helped to combine a plurality of abnormal data indexes, analyze abnormal reasons and assist in decision making reference.

Description

Technical Field

[0001] The present invention relates to the field of deep mining and analysis of ship AIS data, and in particular to a method and system for real-time abnormal monitoring of global shipping data. Background Art

[0002] At present, emergencies occur frequently around the world, and the freight volume and freight rates of the international shipping industry are significantly affected. Currently, publicly available shipping indices such as the Baltic Dry Index (BDI), which reflects the health of global shipping and the economy, and domestic indicators such as the China Container Freight Index (CCFI) are all single shipping indicators. However, the information provided by a single indicator is limited, and it can often only reflect one aspect of the problem, but not the whole picture of the problem, which may lead to decision-making bias and misleading. At the same time, there is also the problem of inefficiency. Users need to check, compare and calculate one by one to find the indicators of shipping anomalies from these numerous indicators, which will make it impossible for users to make quick judgments, reducing the efficiency and accuracy of ship operations. Summary of the invention

[0003] Aiming at the problem that there are a large number of shipping operation data indicators, it is impossible to quickly screen out all shipping indicators that meet the abnormal rules, and it is impossible to summarize and intuitively display the global shipping abnormal data, a method and system for real-time abnormal monitoring of global shipping data are proposed, which can quickly screen out all shipping indicators that meet the abnormal rules, and summarize and intuitively display the global shipping abnormal data through the system, so as to better help users obtain abnormal data and analyze the causes of abnormalities.

[0004] The specific technical solutions are as follows:

[0005] A method for real-time abnormal monitoring of global shipping data, comprising the following specific steps:

[0006] S1: Setting shipping index dimensions and generating a shipping index data list: AIS data is collected through the AIS data center and classified according to shipping index dimensions to generate a shipping index data list, and multiple mapping relationships between route indicators and economic indicators are established in the list; the shipping index dimensions include: environmental dimension, route dimension, and economic dimension;

[0007] S2: Setting shipping abnormal data judgment rules: defining shipping abnormal data judgment rules, including: setting the thresholds of each indicator parameter in the abnormal data judgment rules according to the current market information and historical information, the indicator parameters include the moving average window size corresponding to the shipping indicator, the daily time specified cycle, the weekly time specified cycle, the number of days exceeding the increase or decrease range, and the increase or decrease range;

[0008] S3: Determine the abnormal data in the shipping index data list in S1 according to the shipping abnormal data judgment rules in S2: perform simple moving smoothing calculation on the shipping index data obtained in S1 through the moving average window size set in S2 to obtain a set m1; calculate the percentage change of the value of the data in the set m1 to obtain a set p; determine whether the number of days in the specified time period in the set p that is greater than or equal to the increase or decrease range set in S2 reaches the number of days exceeding the increase or decrease range set in S2; if reached, it is abnormal data;

[0009] S4: Visual display of shipping abnormal data: Based on the route, the proportion of abnormal data on the route is counted, and the increase or decrease in the abnormal data is reflected by the route color. Based on the specified route, other abnormal indicator data of the route are queried.

[0010] Preferably, the shipping indicators are collected into the shipping data middle-end system through massive ship AIS data, ship deadweight tonnage and ship number information at the port, and the shipping indicators in each shipping indicator dimension are generated by analyzing the data set in the shipping data middle-end system to comprehensively reflect the shipping data.

[0011] Preferably, the environmental dimensions include: geographical location, weather; the route dimensions include: ship type, load, cargo type, route information; the economic dimensions include: freight rate, shipping cycle.

[0012] Preferably, the abnormal data includes: the indicator data continues to rise or fall by more than a specified range within a specified time period, or the number of times the indicator data rises or falls by more than a specified range within a specified time period reaches a specified number; the specified time period includes:

[0013] Long-term: duration greater than or equal to 8 weeks;

[0014] Medium term: duration greater than or equal to 3 weeks and less than 8 weeks;

[0015] Short-term: less than 3 weeks;

[0016] Rising: refers to the data gradually increasing in a specified time period;

[0017] Decline: refers to the data gradually becoming smaller in a specified time period.

[0018] Preferably, the parameters of the shipping abnormal data judgment rule include:

[0019] Moving average window size (ma): indicates the number of data points used to calculate the moving average. You can select different numbers of original indicator data;

[0020] Days: indicates the specified time period in days.

[0021] Weekly time specified period (weeks): indicates the specified time period, the unit is week;

[0022] Exceeding the number of days of increase or decrease (ndays): indicates that N abnormalities have occurred within the specified time period. The unit of the specified time period is day, and the set time period cannot exceed days. If this parameter is not set, it means that the price continues to rise or fall within the period of days or weeks.

[0023] Percents: The increase or decrease in a specified time period, expressed as a percentage.

[0024] Preferably, the specific process of the abnormal rules and shipping index data calculation and judgment method is as follows:

[0025] S31: taking the first rule, namely rule i, from the set abnormal data judgment rule list according to the order; the abnormal data judgment rule list is formed by integrating all the set abnormal data judgment rules;

[0026] S32: Obtain a list of shipping data indicators from S1, and take the first indicator data set m;

[0027] S33: Obtain the value of the parameter ma from the rule i, perform a simple moving smoothing calculation on the indicator data set m, and obtain a new smoothed data set m1;

[0028] S34: Calculate the percentage change of the value of the data set m1 starting from the first data x1, such as the percentage of x2 is (x2-x1) / x1, and complete the calculation for all data in the set m1 in sequence to obtain the set p;

[0029] S35: Obtain the values ​​of the days, ndays and percents parameters in the rule i, and compare the set p obtained in S34 in reverse order from the last value in the set p. If the number of times that the value from the last value to the last days in the set p is greater than or equal to the percents parameter is greater than or equal to ndays, then it is determined that the indicator data meets the exception rule and is abnormal data; if ndays is not obtained and only the percents parameter exists, if the value from the last value to the last days in the set p is greater than or equal to the percents parameter, then the indicator data meets the exception rule and is abnormal data;

[0030] S36: using the rule i to repeat steps S33-S35 for all subsequent indicator data in the list to perform calculation and judgment;

[0031] S37: Obtain the second rule in the abnormal data judgment rule list and repeat the steps S33-S36 for all indicator data again to perform calculation and judgment, until all the rules in the abnormal data judgment rule list are used to complete the calculation and judgment of all indicator data.

[0032] Preferably, the simple moving smoothing calculation is:

[0033] Ft=(At-1+At-2+At-3+…+At-n) / n

[0034] Among them, Ft is the result value of simple moving average; n is the moving average window size (ma) parameter; At-1, At-2,…, At-n, etc. are the n consecutive indicator data values ​​before time t in the set m1.

[0035] Preferably, the abnormal data projected on the map at the place where the data anomaly occurs is displayed by marking on the map according to the names of the origin and destination and the corresponding longitude and latitude in the single abnormal data; the thickness of the link line is determined to be 1 pixel, 3 pixels, and 6 pixels respectively according to the "short-term", "medium-term", and "long-term" attributes of the data; the color of the connecting line is red when the abnormal data is rising; the color of the connecting line is green when the abnormal data is falling; the connecting line has an arrow pointing from the origin to the destination.

[0036] A global shipping data real-time abnormal monitoring system, comprising:

[0037] Data acquisition module: used to obtain global shipping index data and generate a shipping index data list;

[0038] Shipping abnormal data judgment rule setting module: including: defining indicator parameters for judging shipping abnormal data, and parameter thresholds of each indicator;

[0039] Timing module: The data acquisition module is mobilized at a specified time to obtain global shipping index data, and the shipping abnormality data module is mobilized at a specified time to judge shipping abnormality data;

[0040] The shipping abnormal data judgment module includes: using the abnormal data judgment rule and the shipping index data to perform calculations, and judging whether the shipping index data is abnormal data to generate an abnormal data index list;

[0041] Shipping abnormal data visualization module: All abnormal data are displayed in data lists, curve graphs, and maps projecting the location where the data abnormality occurs. The displayed content includes the increase or decrease of the abnormal data indicators and the length of the cycle.

[0042] Beneficial effects:

[0043] The present invention proposes a method and system for real-time anomaly monitoring of global shipping data. The present invention can quickly screen out all shipping indicators that meet the anomaly rules, and summarize the global shipping anomaly data on the map to intuitively display them, so as to better help users to know the anomaly data and analyze the anomaly causes. First, the present invention generates shipping indicators based on the data such as the type of cargo, load, origin and destination of the shipping ship itself, and the global shipping capacity can be effectively reflected through the shipping indicators; the abnormal operation data can be automatically screened out by using the abnormal rule setting, and the decision-making analysis support can be provided to the user in a timely manner; at the same time, the abnormal frequency of a single shipping indicator in multiple continuous cycles or within a specified range can be analyzed, solving the problem that the shipping indicator can only analyze and display a single indicator; finally, the present invention displays all the abnormal indicators on the map, and the display content includes the fluctuation of the abnormal data indicators, the length of the cycle, and the abnormal concentrated areas can be displayed vividly, helping users to combine multiple abnormal data indicators, analyze the abnormal causes and assist in decision-making reference. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flow chart of a method for real-time anomaly monitoring of global shipping data.

[0045] Figure 2 A structural diagram of a real-time anomaly monitoring system for global shipping data.

[0046] Figure 3 Schematic diagram of the visualization of abnormal data curves.

[0047] Figure 4 Schematic diagram of visualizing abnormal data on a map. DETAILED DESCRIPTION

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] like Figure 1 As shown, a method for real-time abnormal monitoring of global shipping data includes:

[0050] S1: Setting shipping index dimensions and generating a shipping index data list: AIS data is collected through the AIS data center and classified according to shipping index dimensions to generate a shipping index data list, and multiple mapping relationships between route indicators and economic indicators are established in the list; the shipping index dimensions include: environmental dimension, route dimension, and economic dimension;

[0051] S2: Setting shipping abnormal data judgment rules: defining shipping abnormal data judgment rules, including: setting the thresholds of each indicator parameter in the abnormal data judgment rules according to the current market information and historical information, the indicator parameters include the moving average window size corresponding to the shipping indicator, the daily time specified cycle, the weekly time specified cycle, the number of days exceeding the increase or decrease range, and the increase or decrease range;

[0052] S3: Determine the abnormal data in the shipping index data list in S1 according to the shipping abnormal data judgment rules in S2: perform simple moving smoothing calculation on the shipping index data obtained in S1 through the moving average window size set in S2 to obtain a set m1; calculate the percentage change of the value of the data in the set m1 to obtain a set p; determine whether the number of days in the specified time period in the set p that is greater than or equal to the increase or decrease range set in S2 reaches the number of days exceeding the increase or decrease range set in S2; if reached, it is abnormal data;

[0053] S4: Visual display of shipping abnormal data: Based on the route, the proportion of abnormal data on the route is counted, and the increase or decrease in the abnormal data is reflected by the route color. Based on the specified route, other abnormal indicator data of the route are queried.

[0054] Preferably, the shipping indicators are collected into the shipping data middle-end system through massive ship AIS data, ship deadweight tonnage and ship number information at the port, and the shipping indicators in each shipping indicator dimension are generated by analyzing the data set in the shipping data middle-end system to comprehensively reflect the shipping data.

[0055] Preferably, the environmental dimensions include: geographical location, weather; the route dimensions include: ship type, load, cargo type, route information; the economic dimensions include: freight rate, shipping cycle.

[0056] Preferably, the abnormal data is defined as the indicator data rising or falling by more than a specified range continuously within a specified time period, or rising or falling by more than a specified range for a specified number of times within a specified time period, which is defined as data abnormality; the definition of the specified time period includes:

[0057] Long-term: duration greater than or equal to 8 weeks;

[0058] Medium term: duration greater than or equal to 3 weeks and less than 8 weeks;

[0059] Short-term: less than 3 weeks;

[0060] Rising: refers to the data gradually increasing in a specified time period;

[0061] Decline: refers to the data gradually becoming smaller in a specified time period.

[0062] Preferably, the parameter settings of the shipping abnormal data judgment rule are as follows:

[0063] Moving average window size (ma): indicates the number of data points used to calculate the moving average. You can select different numbers of original indicator data;

[0064] Day time specification (days): indicates the specified time period, in days;

[0065] Weekly time specification (weeks): indicates the specified time period, in weeks;

[0066] Continuous data anomaly days (ndays): indicates that N anomalies have occurred within the specified time period. The unit of the specified time period is day, and the set time period cannot exceed days. If this parameter is not set, it means that the price continues to rise or fall within the period of days or weeks.

[0067] Percents: The increase or decrease in a specified time period, expressed as a percentage.

[0068] Preferably, the specific process of the abnormal rules and shipping index data calculation and judgment method is as follows:

[0069] S31: taking the first rule, namely rule i, from the set abnormal data judgment rule list according to the order; the abnormal data judgment rule list is formed by integrating all the set abnormal data judgment rules;

[0070] S32: Obtain a list of shipping data indicators from S1, and take the first indicator data set m;

[0071] S33: Obtain the value of the parameter ma from the rule i, perform a simple moving smoothing calculation on the indicator data set m, and obtain a new smoothed data set m1;

[0072] S34: Calculate the percentage change of the value of the data set m1 starting from the first data x1, such as the percentage of x2 is (x2-x1) / x1, and complete the calculation for all data in the set m1 in sequence to obtain the set p;

[0073] S35: Obtain the values ​​of the days, ndays and percents parameters in the rule i, and compare the set p obtained in S34 in reverse order from the last value in the set p. If the number of times that the value from the last value to the last days in the set p is greater than or equal to the percents parameter is greater than or equal to ndays, then it is determined that the indicator data meets the exception rule and is abnormal data; if ndays is not obtained and only the percents parameter exists, if the value from the last value to the last days in the set p is greater than or equal to the percents parameter, then the indicator data meets the exception rule and is abnormal data;

[0074] S36: using the rule i to repeat steps S33-S35 for all subsequent indicator data in the list to perform calculation and judgment;

[0075] S37: Obtain the second rule in the abnormal data judgment rule list and repeat the steps S33-S36 for all indicator data again to perform calculation and judgment, until all the rules in the abnormal data judgment rule list are used to complete the calculation and judgment of all indicator data.

[0076] Preferably, the simple moving smoothing calculation is:

[0077] Ft=(At-1+At-2+At-3+…+At-n) / n

[0078] Among them, Ft is the result value of simple moving average; n is the moving average window size (ma) parameter; At-1, At-2,…, At-n, etc. are the n consecutive indicator data values ​​before time t in the set m1.

[0079] Preferably, the abnormal data projected on the map at the place where the data anomaly occurs is displayed by marking on the map according to the names of the origin and destination and the corresponding longitude and latitude in the single abnormal data; the thickness of the link line is determined to be 1 pixel, 3 pixels, and 6 pixels respectively according to the "short-term", "medium-term", and "long-term" attributes of the data; the connection line is determined to be green or red according to whether the data is rising or falling; the connection line has an arrow direction pointing from the origin to the destination.

[0080] Example 1: The specific process of determining whether indicator data A is abnormal data and data visualization is as follows:

[0081] 1) Get the latest shipping data indicators, such as indicator A data as follows:

[0082] Table 1 Partial data of indicator data A

[0083] time Numeric December 26, 2022 4246233 December 27, 2022 368379 ... November 4, 2023 413613 November 5, 2023 492190 November 6, 2023 507237 November 7, 2023 476579 November 8, 2023 347901 November 9, 2023 302461 November 10, 2023 492305 November 11, 2023 646339 November 13, 2023 720090 November 14, 2023 790784

[0084] 2) Set the abnormal data judgment rule R, such as "short-term rise: daily MA7 continuous rise", the parameters are as follows:

[0085] Table 2 Abnormal data judgment rules R

[0086] parameter value ma 7 days 3 percents 5 ndays Not set

[0087] 3) Calculate the MA7 data of indicator data A in the past 4 days and the MA7 rise and fall range in the past 3 days according to the abnormal rule R;

[0088] Table 3 Abnormal rules and calculated values ​​of shipping index data

[0089] time Numeric MA7 Value MA7 rise and fall November 10, 2023 492305 433183.7143 November 11, 2023 646339 466430.2857 7.13％ November 13, 2023 720090 498987.4286 6.52％ November 14, 2023 790784 539494.1429 7.51％

[0090] From Table 3, we can see that indicator data A meets the abnormal rule that the increase of MA7 values ​​in the past 3 days is greater than 5%, so the indicator data is abnormal data;

[0091] 4) If Figure 3 As shown, the abnormal data is displayed on the curve graph, where Figure 3 The shipping index in the index is a general term for all indicator data; at the same time, the global shipping capacity is reflected through shipping indicators;

[0092] 5) Mark the origin and destination names and corresponding longitude and latitude in the single abnormal data on the map; determine the thickness of the link line to be 1 pixel, 3 pixels, and 6 pixels respectively according to the "long-term", "medium-term", and "short-term" attributes of the data; determine whether the connecting line is green or red according to whether the data is rising or falling; for example, "ships from India to the UAE" meet the rule "short-term decline: MA5 has fallen more than 5 times in the past 7 days and is greater than 5%", and a 1-pixel green connecting line will be used to connect India and the UAE; the arrow on the connecting line points from the origin to the destination;

[0093] 6) If Figure 4 As shown, after the traversal is completed, the abnormal data is displayed on the map.

[0094] like Figure 2 As shown, a global shipping data real-time abnormal monitoring system includes:

[0095] Data acquisition module: used to obtain global shipping index data and generate a shipping index data list;

[0096] Shipping abnormal data judgment rule setting module: including: defining indicator parameters for judging shipping abnormal data, and parameter thresholds of each indicator;

[0097] Timing module: The data acquisition module is mobilized at a specified time to obtain global shipping index data, and the shipping abnormality data module is mobilized at a specified time to judge shipping abnormality data;

[0098] The shipping abnormal data judgment module includes: using the abnormal data judgment rule and the shipping index data to perform calculations, and judging whether the shipping index data is abnormal data to generate an abnormal data index list;

[0099] Shipping abnormal data visualization module: All abnormal data are displayed in data lists, curve graphs, and maps projecting the location where the data abnormality occurs. The displayed content includes the increase or decrease of the abnormal data indicators and the length of the cycle.

[0100] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for real-time abnormal monitoring of global shipping data, characterized in that: include: S1: Setting shipping index dimensions and generating a shipping index data list: AIS data is collected through the AIS data center and classified according to shipping index dimensions to generate a shipping index data list, and multiple mapping relationships between route indicators and economic indicators are established in the list; the shipping index dimensions include: environmental dimension, route dimension, and economic dimension; S2: Setting shipping abnormal data judgment rules: defining shipping abnormal data judgment rules, including: setting the thresholds of each indicator parameter in the abnormal data judgment rules according to the current market information and historical information, the indicator parameters include the moving average window size corresponding to the shipping indicator, the daily time specified cycle, the weekly time specified cycle, the number of days exceeding the increase or decrease range, and the increase or decrease range; S3: Determine the abnormal data in the shipping index data list in S1 according to the shipping abnormal data judgment rules in S2: perform simple moving smoothing calculation on the shipping index data obtained in S1 through the moving average window size set in S2 to obtain a set m1; calculate the percentage change of the value of the data in the set m1 to obtain a set p; determine whether the number of days in the specified time period in the set p that is greater than or equal to the increase or decrease range set in S2 reaches the number of days exceeding the increase or decrease range set in S2; if reached, it is abnormal data; S4: Visual display of shipping abnormal data: Based on the route, the proportion of abnormal data on the route is counted, and the increase or decrease in the abnormal data is reflected by the route color. Based on the specified route, other abnormal indicator data of the route are queried.

2. A method for real-time abnormal monitoring of global shipping data according to claim 1, characterized in that: The shipping indicators are collected through massive ship AIS data, ship deadweight tonnage and ship number information in the port into the shipping data middle platform system, and the shipping indicators in each shipping indicator dimension are generated by analyzing the data set in the shipping data middle platform system to comprehensively reflect the shipping data.

3. A method for real-time abnormal monitoring of global shipping data according to claim 1, characterized in that: The environmental dimensions include: geographical location and weather; the route dimensions include: ship type, load, cargo type, and route information; the economic dimensions include: freight rates and shipping cycles.

4. A method for real-time abnormal monitoring of ball shipping data according to claim 1, characterized in that: The abnormal data include: the index data continues to rise or fall by more than a specified range within a specified time period, or the index data rises or falls by more than a specified range for a specified number of times within a specified time period; the specified time period includes: Long-term: duration greater than or equal to 8 weeks; Medium term: greater than or equal to 3 weeks and less than 8 weeks; Short-term: less than 3 weeks; Rising: refers to the data gradually increasing in a specified time period; Decline: refers to the data gradually becoming smaller in a specified time period.

5. A method for real-time abnormal monitoring of global shipping data according to claim 1, characterized in that: The parameters of the shipping abnormal data judgment rule include: Moving average window size (ma): indicates the number of data points used to calculate the moving average. You can select different numbers of original indicator data; Days: indicates the specified time period in days. Weekly time specified period (weeks): indicates the specified time period, the unit is week; Exceeding the number of days of increase or decrease (ndays): indicates that N abnormalities have occurred within the specified time period. The unit of the specified time period is day, and the set time period cannot exceed days. If this parameter is not set, it means that the price continues to rise or fall within the period of days or weeks. Percents: The increase or decrease in a specified time period, expressed as a percentage.

6. A method for real-time abnormal monitoring of global shipping data according to claim 1, characterized in that: The specific process of the abnormal rules and shipping index data calculation and judgment method is as follows: S31: taking the first rule, namely rule i, from the set abnormal data judgment rule list according to the order; the abnormal data judgment rule list is formed by integrating all the set abnormal data judgment rules; S32: Obtain a list of shipping data indicators from S1, and take the first indicator data set m; S33: Obtain the value of the parameter ma from the rule i, perform a simple moving smoothing calculation on the indicator data set m, and obtain a new smoothed data set m1; S34: Calculate the percentage change of the value of the data set m1 starting from the first data x1, such as the percentage of x2 is (x2-x1) / x1, and complete the calculation for all data in the set m1 in sequence to obtain the set p; S35: Obtain the values ​​of the days, ndays and percents parameters in the rule i, and compare the set p obtained in S34 in reverse order from the last value in the set p. If the number of times that the value from the last value to the last days in the set p is greater than or equal to the percents parameter is greater than or equal to ndays, then it is determined that the indicator data meets the exception rule and is abnormal data; if ndays is not obtained and only the percents parameter exists, if the value from the last value to the last days in the set p is greater than or equal to the percents parameter, then the indicator data meets the exception rule and is abnormal data; S36: using the rule i to repeat steps S33-S35 for all subsequent indicator data in the list to perform calculation and judgment; S37: Obtain the second rule in the abnormal data judgment rule list and repeat the steps S33-S36 for all indicator data again to perform calculation and judgment, until all the rules in the abnormal data judgment rule list are used to complete the calculation and judgment of all indicator data.

7. A method for real-time abnormal monitoring of global shipping data according to claim 6, characterized in that: The simple moving smoothing calculation is: Ft=(At-1+At-2+At-3+…+At-n) / n Among them, Ft is the result value of simple moving average; n is the moving average window size (ma) parameter; At-1, At-2,…, At-n, etc. are the n consecutive indicator data values ​​before time t in the set m1.

8. A method for real-time abnormal monitoring of global shipping data according to claim 1, characterized in that: The abnormal data projected on the map where the abnormal data occurs is displayed by marking the origin and destination names and the corresponding longitude and latitude in the single abnormal data on the map; according to the "short-term" and The "medium term" and "long term" attributes determine that the thickness of the link line is 1 pixel, 3 pixels, and 6 pixels respectively; the color of the link line is red when the abnormal data is rising; the color of the link line is green when the abnormal data is falling; the link line has an arrow pointing from the origin to the destination.

9. A global shipping data real-time abnormality monitoring system formed based on the method described in any one of claims 1 to 8, characterized in that: include: Data acquisition module: used to obtain global shipping index data and generate a shipping index data list; Shipping abnormal data judgment rule setting module: including: defining indicator parameters for judging shipping abnormal data, and parameter thresholds of each indicator; Timing module: The data acquisition module is mobilized at a specified time to obtain global shipping index data, and the shipping abnormality data module is mobilized at a specified time to judge shipping abnormality data; The shipping abnormal data judgment module includes: using the abnormal data judgment rule and the shipping index data to perform calculations, and judging whether the shipping index data is abnormal data to generate an abnormal data index list; Shipping abnormal data visualization module: All abnormal data are displayed in data lists, curve graphs, and maps projecting the location where the data abnormality occurs. The displayed content includes the increase or decrease of the abnormal data indicators and the length of the cycle.

Images