Ais data quality evaluation method and device, electronic equipment, readable storage medium and chip

Abstract

Embodiments of the present application provide an AIS data quality evaluation method, device, electronic equipment, readable storage medium and chip, wherein the AIS data quality evaluation method comprises: acquiring AIS data of a plurality of ships; determining a sea area type corresponding to each ship; determining a data update interval threshold corresponding to each ship according to regional channel attributes; determining an update frequency score; determining a data integrity score according to ship static data and ship dynamic data; determining a time synchronization score according to equipment time; determining a signal stability score according to signal strength of the AIS data; determining an initial weight; determining at least one focused index according to a ship type and regional operation attributes corresponding to each ship; determining a dimension weight according to the focused index and a plurality of initial weights; and determining a comprehensive quality index of the ship according to the dimension weight and a dimension score. Through the scheme of the present application, multi-dimensional analysis of AIS data is realized, and the accuracy of AIS data quality evaluation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of AIS data processing, in particular to an AIS data quality evaluation method and device, electronic equipment, readable storage medium and chip. BACKGROUND

[0002] At present, with the rapid development of global shipping industry, the importance of the ship automatic identification system (AIS) as a key technology to ensure navigation safety and efficiency is increasingly prominent.

[0003] However, the current AIS data quality evaluation mainly relies on manual inspection, and is limited to single dimension such as data integrity and accuracy, and can only evaluate the quality of AIS data from a single dimension, ignoring key indicators such as signal stability and time synchronization, and it is difficult to evaluate a large number of AIS data generated at high speed in real time, and the quality evaluation of AIS data has limitations. SUMMARY

[0004] The embodiments of the present application provide an AIS data quality evaluation method, device, electronic equipment, readable storage medium and chip, which can solve the problem that the quality of AIS data can only be evaluated from a single dimension, key indicators such as signal stability and time synchronization are ignored, and the quality evaluation of AIS data has limitations.

[0005] Therefore, the embodiments of the first aspect of the present application provide an AIS data quality evaluation method.

[0006] The embodiments of the second aspect of the present application provide an AIS data quality evaluation device.

[0007] The embodiments of the third aspect of the present application provide an electronic equipment.

[0008] The embodiments of the fourth aspect of the present application provide a readable storage medium.

[0009] The embodiments of the fifth aspect of the present application provide a chip.

[0010] To achieve the above object, the embodiment of the first aspect of the present application provides an AIS data quality evaluation method, comprising: acquiring AIS data of a plurality of ships, the AIS data comprising ship static data, ship dynamic data and ship type; determining a sea area type corresponding to each ship, the sea area type comprising regional operation attribute and regional waterway attribute; determining a data update interval threshold corresponding to each ship according to the regional waterway attribute; determining an update frequency score according to the update frequency of the AIS data of the ship and the data update interval threshold; determining a data integrity score according to the ship static data and the ship dynamic data; determining a device time corresponding to the ship, and determining a time synchronization score according to the device time and the world standard time; determining a signal stability score; determining initial weights, the initial weights comprising a first initial weight corresponding to the update frequency score, a second initial weight corresponding to the integrity score, a third initial weight corresponding to the time synchronization score and a fourth initial weight corresponding to the signal stability score; determining at least one emphasis index according to the ship type and the regional operation attribute corresponding to each ship, the emphasis index comprising a first emphasis index, a second emphasis index, a third emphasis index and a fourth emphasis index; determining dimension weights of the update frequency score, the integrity score, the time synchronization score and the signal stability score according to the emphasis index and the plurality of initial weights; determining a comprehensive quality index of the ship according to the dimension weights and dimension scores, the dimension scores comprising the update frequency score, the integrity score, the time synchronization score and the signal stability score.

[0011] The AIS data quality evaluation method provided by the present application constructs a multi-dimensional dynamic quality index system from four dimensions of data update frequency, data integrity, time synchronization and signal stability. By comprehensively evaluating the four indexes of update frequency, data integrity, time synchronization and signal stability in the AIS data, the overall control of the AIS data quality is realized. The traditional data quality evaluation method is often limited to a single dimension such as data integrity or data accuracy, thereby ignoring key indicators such as signal stability and time synchronization. The AIS data quality evaluation method of the present application adds advanced indexes such as update frequency and signal strength on the basis of the evaluation of data integrity, signal stability and time synchronization, ensuring the comprehensiveness of the AIS data quality evaluation, thereby improving the accuracy of the data quality evaluation of the shipping enterprise and helping the enterprise to timely discover and solve potential data problems.

[0012] The initial weights corresponding to the four dimensions of data update frequency, data integrity, time synchronization and signal stability are set, and the weight is dynamically adjusted according to the ship type and the regional operation attribute, thereby enhancing the flexibility and pertinence of the data evaluation and prioritizing the data quality of key scenarios.

[0013] In the technical solution, after determining the comprehensive quality index of the ship according to the dimension weight and the dimension score, the following steps are further included: taking the electronic chart as a base, dividing the electronic chart into a plurality of grid areas according to a 1*1 nautical mile grid, determining the average value of the comprehensive quality indexes of the plurality of ships in the grid area, taking the average value as a grid comprehensive quality index score, coloring the grid area according to the grid comprehensive quality index score, and determining a global heat map.

[0014] In the technical solution, the AIS monitored sea area is divided into a plurality of uniform grid areas according to a 1*1 nautical mile grid based on the electronic chart as a geographical base, the grid comprehensive quality index score of each grid area is determined by averaging the CQI values of all ships in each grid area, and the grid area is colored according to the plurality of grid comprehensive quality index scores to determine a global heat map. The layer corresponding to the electronic chart is below the layer corresponding to the global heat map, that is, the global heat map displays the data quality distribution of the entire sea area by being overlaid on the electronic chart.

[0015] It can be understood that the global heat map is used to visually display the comprehensive quality indexes of the ships in the plurality of sea areas, which reduces the workload of the user for quality assessment, helps the user to quickly identify high-risk areas, and improves the efficiency of data quality assessment.

[0016] Further, the global heat map is used to determine the correspondence between the ships and the grid areas, associate the plurality of ships with one grid area, and lay the foundation for subsequent determination of abnormal ship data and early warning based on the comprehensive quality index. The global heat map is used as a guide to form a complete analysis chain of the global, regional and single ship, improve the data processing efficiency and the intelligence of data quality assessment, and reduce the data processing workload. In addition, the grid area is used to process the comprehensive quality indexes of the plurality of ships, which can quickly locate the abnormal ships and improve the response speed of the AIS data quality assessment.

[0017] In any of the above technical solutions, optionally, after determining the global heat map, the following steps are further included: determining a four-dimensional index score corresponding to the ship according to the plurality of dimension scores; determining a historical trend curve and an abnormal event time axis according to the plurality of four-dimensional index scores; and determining a core panel corresponding to the ship according to the four-dimensional index score, the historical trend curve and the abnormal event time axis.

[0018] In the scheme, the four-dimensional index score is determined based on the update frequency score, the integrity score, the time synchronization score and the signal stability score, the four-dimensional index score of the ship is recorded continuously in a preset time period, the broken line graph is drawn according to the time axis, the change trend of the scores of each dimension is displayed, and the historical trend curve is determined. And according to the time axis and the preset abnormal threshold corresponding to the multiple dimension scores, the abnormal event time axis is determined, and the abnormal events are arranged in chronological order. The four-dimensional index score, the historical trend curve and the abnormal event time axis are integrated into the core panel of the ship, wherein the four-dimensional index score is displayed in the form of a dashboard in the core panel.

[0019] Understandably, the way of integrating the four-dimensional index score, the historical trend curve and the abnormal event time axis through the core panel improves the pertinence of data quality evaluation of a single ship. By setting the core panel, the data evaluation result is converted into the form of intuitive charts and trend graphs, the overall condition and change trend of the data quality are visualized, which helps users make more accurate choices and improves the data quality evaluation effect of users.

[0020] In any of the above technical solutions, optionally, the dimension weight corresponding to the update frequency score, the integrity score, the time synchronization score and the signal stability score is determined according to the focus index and the multiple initial weights, comprising: determining the dimension weight corresponding to the update frequency score according to the first focus index and the first initial weight; determining the dimension weight corresponding to the integrity score according to the second focus index and the second initial weight; determining the dimension weight corresponding to the time synchronization score according to the third focus index and the third initial weight; determining the dimension weight corresponding to the signal stability score according to the fourth focus index and the fourth initial weight.

[0021] In the scheme, the dimension weight corresponding to the update frequency score, the dimension weight corresponding to the integrity score, the dimension weight corresponding to the time synchronization score and the dimension weight corresponding to the signal stability score are determined according to the focus index and the multiple initial weights. The weight requirements of different types of ships in different regions are met, so that the dimension weight is adapted to the ship type and the region type, thereby improving the accuracy of multi-dimensional AIS data quality evaluation.

[0022] Specifically, the emphasis indicators include a first emphasis indicator, a second emphasis indicator, a third emphasis indicator and a fourth emphasis indicator, wherein the first emphasis indicator emphasizes update frequency, the second emphasis indicator emphasizes data integrity, the third emphasis indicator emphasizes time synchronization, and the fourth emphasis indicator emphasizes signal stability. The initial weights include a first initial weight, a second initial weight, a third initial weight and a fourth initial weight, wherein the first initial weight corresponds to the update frequency score, the second initial weight corresponds to the integrity score, the third initial weight corresponds to the time synchronization score, and the fourth initial weight corresponds to the signal stability score, and the initial weights are preset values. At least one emphasis indicator corresponding to the ship is determined according to the ship type and the regional operation attribute corresponding to each ship. The corresponding relationship between the ship type and the emphasis indicator, the corresponding relationship between the regional type and the emphasis indicator, and the preset weight adjustment parameter corresponding to the emphasis indicator are obtained by presetting, for example, when the ship type is a research ship, the third emphasis indicator corresponding to the ship is determined, and when the regional type is a port operation area, the first emphasis indicator corresponding to the port operation area is determined, that is, when the research ship sails in the port operation area, the first emphasis indicator and the third emphasis indicator of the ship are determined to meet the update frequency and time synchronization requirements. The dimension weight corresponding to the update frequency score is determined according to the first emphasis indicator and the first initial weight, that is, the first initial weight is adjusted by the preset weight adjustment parameter corresponding to the first emphasis indicator, for example, the preset weight adjustment parameter corresponding to the first emphasis indicator is +15%, the first initial weight is set to 30%, and the dimension weight corresponding to the update frequency score is 30%+15%, that is, the dimension weight corresponding to the update frequency score is 45%; the preset weight adjustment parameter corresponding to the third emphasis indicator is -10%, the third initial weight is set to 20%, and the dimension weight corresponding to the synchronization score is 20%-10%, that is, the dimension weight corresponding to the synchronization score is 10%.

[0023] It can be understood that the dynamic weight is set on the basis of the initial weight, at least one emphasis indicator is determined according to the ship type and the regional operation attribute corresponding to each ship, and the initial weight is updated through the at least one emphasis indicator, so as to meet the sailing requirements of different types of ships in different sea areas and improve the accuracy of AIS data quality evaluation.

[0024] In any of the technical solutions above, optionally, the comprehensive quality index of the ship is determined according to the dimension weight and the dimension score, including: determining an update frequency quality index according to the dimension weight corresponding to the update frequency score and the update frequency score; determining an integrity quality index according to the dimension weight corresponding to the integrity score and the integrity score; determining a time synchronization quality index according to the dimension weight corresponding to the time synchronization score and the time synchronization score; determining a signal stability quality index according to the dimension weight corresponding to the signal stability score and the signal stability score; and determining the comprehensive quality index according to the update frequency quality index, the integrity quality index, the time synchronization quality index and the signal stability quality index.

[0025] In the present solution, each dimension score is multiplied by the adjusted dimension weight to generate a quality index of the dimension, and the quality index includes an update frequency quality index, an integrity quality index, a signal stability quality index and a time synchronization quality index. The update frequency quality index, the integrity quality index, the signal stability quality index and the time synchronization quality index are added to determine the final comprehensive quality index.

[0026] It can be understood that the scores of the four dimensions of update frequency, integrity, time synchronization and signal stability are integrated into a single index (CQI) through weighted summation, which realizes comprehensive evaluation of AIS data of a single ship and provides reliable data support for subsequent abnormal signal evaluation.

[0027] In any of the technical solutions above, optionally, the AIS data quality evaluation method further includes: determining at least one inferior ship according to the comprehensive quality indexes of the plurality of ships in the grid area; obtaining a quality score threshold; and determining that the data quality type of the ship is a first type when at least one dimension score of the ship is less than the quality score threshold and the ship is the inferior ship.

[0028] In the present solution, on the basis of dividing the grid area through the global heat map, the comprehensive quality indexes of all ships in the grid area are summarized to determine at least one inferior ship in the area. At least one of the four dimension scores of the inferior ship is less than the quality score threshold, and the data quality type of the ship is determined to be the first type. That is, the AIS data quality evaluation result of the ship does not meet the data quality requirement, and the ship needs to be prioritized for maintenance and investigation. The quality score threshold is the average value of the sum of the dimension scores of all ships in the area.

[0029] Understandably, using both grid area filtering and dimensional threshold determination as dual criteria to assess ship data quality further enhances the accuracy and reliability of ship AIS data quality evaluation. Furthermore, by analyzing the comprehensive quality index of all ships within different grid areas, and through parallel analysis of the overall regional AIS data quality and the AIS data quality of individual ships, ship data quality evaluation is grounded in the overall regional data quality, improving the accuracy of ship data quality evaluation in different sea areas and meeting the needs of diverse maritime environments.

[0030] Optionally, in any of the above technical solutions, the AIS data quality assessment method further includes: determining the analysis period; determining multiple comprehensive quality indices of the ship within the analysis period; determining the AIS data quality change parameters corresponding to the ship based on the multiple comprehensive quality indices within the analysis period; obtaining the data quality change threshold; and determining the ship's data quality type as the second type when the AIS data quality change parameter is greater than the data quality change threshold.

[0031] In this scheme, the AIS data quality change parameter is determined by identifying multiple composite quality indices of the vessel within a time period. This parameter is derived from multiple composite quality indices and specifically represents the slope of the fitted analysis period of the multiple composite quality indices, indicating the change in the vessel's composite quality index within that period. A negative value for the AIS data quality change parameter indicates a decline in the vessel's data quality. The analysis period and data quality change threshold are preset values. When the value corresponding to the AIS data quality change parameter exceeds the preset threshold, the vessel's data quality is determined to be in a state of continuous deterioration, requiring preventative maintenance. This indicates the vessel's data quality type is classified as Type II.

[0032] Understandably, by correlating the composite quality index with time periods, we can determine the changes in ship data quality over a given period, identify ships requiring preventative maintenance, and use a second type of ship to identify those with a continuously declining composite quality index. We can then conduct early maintenance on these ships to prevent accidents caused by data quality deterioration, provide early warnings for abnormal ships, and improve the safety of ship navigation.

[0033] In any of the technical solutions above, optionally, the AIS data quality evaluation method further comprises: determining historical AIS data of each grid region in the global heat map according to a plurality of historical trend curves; determining a historical average value corresponding to the grid comprehensive quality index score of the grid region according to the historical AIS data; and determining the first warning type when the grid comprehensive quality index score of the grid region is less than the historical average value or when at least one dimension score of a ship in the grid region is less than the quality score threshold.

[0034] In this solution, for each grid region, historical AIS data corresponding to the region is determined in combination with a historical trend curve, and the historical AIS data includes historical comprehensive quality indexes of all ships in the grid region. When the grid comprehensive quality index score of the grid region is less than the average value of the historical AIS data or at least one dimension score of a single ship in the region is less than the quality score threshold, the ship and the region are determined as the first warning type. The ship and the region of the first warning type are marked with a yellow warning in the electronic chart, and the warning information of the ship and the region is pushed through the platform message center. The grid region and the single ship are associated and analyzed, the AIS data of all ships in a specific region is summarized and analyzed, regional data quality problems are quickly identified, and the efficiency of data quality evaluation is improved.

[0035] It can be understood that the historical average value corresponding to the grid region is used as a dynamic reference to avoid the fixed threshold that cannot adapt to the characteristics of the region. By using the average value of the historical AIS data of the grid region as the threshold, the specificity of different regions in the data quality evaluation process is improved, thereby reducing false positives and improving the accuracy of the warning.

[0036] In any of the technical solutions above, optionally, the AIS data quality evaluation method further comprises: determining a first warning parameter and a second warning parameter, the first warning parameter being less than the second warning parameter; and determining the second warning type when the comprehensive quality index score of a ship in the grid region is less than the first warning parameter or the grid comprehensive quality index score of the grid region is less than the second warning parameter.

[0037] In the scheme, the first early warning parameter and the second early warning parameter are determined, the first early warning parameter is less than the second early warning parameter, the first early warning parameter is used to determine the data quality corresponding to the ship comprehensive quality index, and the second early warning parameter is used to determine the data quality corresponding to the grid comprehensive quality index score of the grid area. Wherein, the first early warning parameter is greater than the quality score threshold, and the second early warning parameter is greater than the quality score threshold. The first early warning parameter and the second early warning parameter are both preset values. When the comprehensive quality score index of the ship in the area is less than the first early warning parameter or the grid comprehensive quality index score of the grid area is less than the second early warning parameter, the early warning type is determined as the second early warning type, and the ship and the area of the second early warning type are marked with red color for early warning in the electronic chart. And the early warning information of the ship and the area is pushed through the combination of platform pop-up window, short message and email. The grid area and the single ship are associated and analyzed, the AIS data of all ships in a specific area are summarized and analyzed, the abnormal data quality of the area or the abnormal data quality of the single ship is alarmed, and the safety risk caused by the data quality problem is reduced.

[0038] It can be understood that by setting the first early warning parameter less than the second early warning parameter, the first early warning parameter is used to determine the data quality corresponding to the ship comprehensive quality index, and the second early warning parameter is used to determine the data quality corresponding to the grid comprehensive quality index score of the grid area. The overall data quality requirement of the area is higher than the single ship quality requirement. On this basis, the risk classification management of the ship and the grid area is realized, the excessive alarm caused by the single threshold is avoided, the operation and maintenance resources are reasonably allocated, and the data quality analysis efficiency is improved.

[0039] Further, by visualizing the first early warning type and the second early warning type in the electronic chart, the user can quickly locate the data quality abnormal area, and improve the efficiency of the user to find the data problem.

[0040] The embodiment of the second aspect of the application provides an AIS data quality evaluation device, comprising: a data acquisition module, configured to acquire AIS data of a plurality of ships, the AIS data comprising ship static data, ship dynamic data and ship type; determining a sea area type corresponding to each ship, the sea area type comprising regional operation attribute and regional channel attribute; a frequency determination module, configured to determine a data update interval threshold corresponding to each ship according to the regional channel attribute; determining an update frequency score according to the update frequency of the AIS data of the acquired ship and the data update interval threshold; a field module, configured to determine a data integrity score according to the ship static data and the ship dynamic data; a time module, configured to determine equipment time corresponding to the ship, and determine a time synchronization score according to the equipment time and the world standard time; a signal determination module, configured to determine a signal stability score according to the signal strength of the AIS data; a dynamic weight module, configured to determine an initial weight, the initial weight comprising a first initial weight corresponding to the new frequency score, a second initial weight corresponding to the integrity score, a third initial weight corresponding to the time synchronization score and a fourth initial weight corresponding to the signal stability score; determining at least one emphasis index according to the ship type and the regional operation attribute corresponding to each ship, the emphasis index comprising a first emphasis index, a second emphasis index, a third emphasis index and a fourth emphasis index; determining a dimension weight corresponding to the update frequency score, the integrity score, the time synchronization score and the signal stability score according to the emphasis index and the plurality of initial weights; a quality evaluation module, configured to determine a comprehensive quality index of the ship according to the dimension weight and the dimension score, the dimension score comprising the update frequency score, the integrity score, the time synchronization score and the signal stability score.

[0041] The AIS data quality evaluation device provided by the application realizes the AIS data quality evaluation method, constructs a multi-dimensional dynamic quality index system from four dimensions of data update frequency, data integrity, time synchronization and signal stability, comprehensively evaluates the four indexes of update frequency, data integrity, time synchronization and signal stability in the AIS data, and realizes comprehensive control of the AIS data quality. On this basis, by setting a global heat map, the corresponding relationship between the ship and the grid area is determined, a plurality of ships and a grid area are associated, the subsequent determination of abnormal ship data and the subsequent warning are prepared, the global heat map is used as a guide, a complete analysis chain of the global, regional and single ship is formed, the data processing efficiency and the intelligentization of data quality evaluation are improved, and the data processing workload is reduced. Moreover, by processing the comprehensive quality indexes of a plurality of ships in a grid area, the abnormal ship can be quickly positioned, and the response speed of the AIS data quality evaluation is improved.

[0042] The embodiment of the third aspect of the application provides an electronic device, comprising a processor, a memory and a program or instructions stored in the memory and executable on the processor, the program or instructions being executed by the processor to implement the steps of the AIS data quality evaluation method in the first aspect.

[0043] The embodiment of the fourth aspect of the application provides a readable storage medium, the readable storage medium storing a program or instructions, the program or instructions being executed by the processor to implement the steps of the AIS data quality evaluation method in the first aspect.

[0044] The embodiment of the fifth aspect of the application provides a chip, comprising a processor and a communication interface, the communication interface being coupled with the processor, the processor being used to run a program or instructions to implement the steps of the AIS data quality evaluation method in the first aspect.

[0045] Additional aspects and advantages of the technical solutions of the application will become apparent from the following description section or be understood through the practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A flowchart of an AIS data quality evaluation method according to one embodiment of the application is shown;

[0047] Figure 2 A structural schematic block diagram of an AIS data quality evaluation device according to one embodiment of the application is shown;

[0048] Figure 3 A structural schematic block diagram of an electronic device according to one embodiment of the application is shown;

[0049] Figure 4 A schematic diagram of a global heat map according to one embodiment of the application is shown;

[0050] Figure 5 A schematic diagram of a historical trend curve according to one embodiment of the application is shown;

[0051] Figure 6 A schematic diagram of a real-time four-dimensional index score according to one embodiment of the application is shown;

[0052] Figure 7 A schematic diagram of an abnormal event timeline according to one embodiment of the application is shown;

[0053] Figure 8 A partial flowchart of an AIS data quality evaluation method according to one embodiment of the application is shown;

[0054] Figure 9 A partial flowchart of an AIS data quality evaluation method according to one embodiment of the application is shown;

[0055] Figure 10 Part of the flowchart of the AIS data quality evaluation method according to an embodiment of the application is shown;

[0056] Figure 11 Part of the flowchart of the AIS data quality evaluation method according to an embodiment of the application is shown;

[0057] Figure 12 Part of the flowchart of the AIS data quality evaluation method according to an embodiment of the application is shown;

[0058] Figure 13 Part of the flowchart of the AIS data quality evaluation method according to an embodiment of the application is shown.

[0059] wherein, Figure 2 and Figure 3 The correspondence between the reference signs and the component names in the drawings is as follows:

[0060] 900: AIS data quality evaluation device; 902: data acquisition module; 904: frequency determination module; 906: field module; 908: time module; 910: signal determination module; 912: dynamic weight module; 914: quality evaluation module; 1000: electronic device; 1110: processor; 1109: memory. DETAILED DESCRIPTION

[0061] In order to more clearly understand the above-mentioned purposes, features and advantages of the embodiments of the application, the embodiments of the application will be further described in detail below in combination with the drawings and specific embodiments. It should be noted that the embodiments of the application and the features in the embodiments can be combined with each other without conflict.

[0062] In the following description, many specific details are set forth in order to provide a thorough understanding of the application, but embodiments of the application can also be implemented in other ways different from those described herein, therefore, the scope of protection of the application is not limited to the specific embodiments disclosed below.

[0063] The embodiments of the application will be described in detail below in combination with the drawings and specific embodiments. Figures 1 to 13 The AIS data quality evaluation method, device, electronic device, readable storage medium and chip provided by the embodiments of the application are described in detail through specific embodiments and application scenarios.

[0064] The embodiments of the application provide an AIS data quality evaluation method, as shown in the figure, the AIS data quality evaluation method comprises: Figure 1

[0065] Step S100: acquiring AIS data of a plurality of ships;​

[0066] Step S102: determining a sea area type corresponding to each ship;

[0067] Step S104: determining a data update interval threshold corresponding to each ship according to the regional waterway attribute;

[0068] Step S106: determining an update frequency score according to the update frequency of the AIS data of the ship and the data update interval threshold;

[0069] Step S108: determining a data integrity score according to the static data of the ship and the dynamic data of the ship;

[0070] Step S110: determining a device time corresponding to the ship, and determining a time synchronization score according to the device time and the world standard time;

[0071] Step S112: determining a signal stability score;

[0072] Step S114: determining an initial weight;

[0073] Step S116: determining at least one emphasis index according to the ship type and the regional operation attribute corresponding to each ship;

[0074] Step S118: determining a dimension weight corresponding to the update frequency score, the integrity score, the time synchronization score and the signal stability score according to the emphasis index and the plurality of initial weights;

[0075] Step S120: determining a comprehensive quality index of the ship according to the dimension weight and the dimension score.

[0076] The AIS data quality evaluation method provided by the application constructs a multi-dimensional dynamic quality index system from four dimensions of data update frequency, data integrity, time synchronization and signal stability, and comprehensively evaluates the four indexes of update frequency, data integrity, time synchronization and signal stability in the AIS data, so as to realize comprehensive control of the AIS data quality. The traditional data quality evaluation method is often limited to a single dimension such as data integrity or data accuracy, thereby ignoring key indexes such as signal stability and time synchronization. The AIS data quality evaluation method of the application adds advanced indexes such as update frequency and signal strength on the basis of the evaluation of data integrity, signal stability and time synchronization, ensures the comprehensiveness of the AIS data quality evaluation, thereby improving the accuracy of the data quality evaluation of the shipping enterprise, and helps the enterprise to discover and solve potential data problems in time.

[0077] The initial weights corresponding to the four dimensions of data update frequency, data integrity, time synchronization and signal stability are set, and the weight adjustment mode is dynamically adjusted according to the ship type and regional operation attribute, so as to enhance the flexibility and pertinence of data evaluation, and to preferentially ensure the data quality of key scenes.

[0078] Specifically, the AIS data of a plurality of ships is acquired, the AIS data being periodically fed back data, the AIS data including ship static data, ship dynamic data and ship type. The ship static data includes ship inherent attribute information such as ship name, size, draft and Maritime Mobile Service Identity (MMSI), and the ship dynamic data includes real-time updated information data of the position, speed and heading of the ship, so as to reflect the current state and moving track of the ship. The ship type is determined according to the working requirement of the ship. For example, container ship and research ship. The sea area type corresponding to the navigation of each ship is determined according to the AIS data fed back by the ship in combination with the radar system and Electronic Chart Display and Information Systems (ECDIS), and the sea area type includes regional operation attribute and regional channel attribute. The regional operation attribute is the sea area type of the sea area where the ship travels, such as port operation area, international channel and fishing area, etc. The regional channel attribute is the width of the channel at the time point corresponding to the AIS data fed back by the ship. The data update interval threshold corresponding to each ship is determined according to the regional channel attribute, and the data update interval threshold is proportional to the width of the channel at the time point corresponding to the AIS data fed back by the ship, i.e. the wider the channel width, the larger the data update interval threshold, and the narrower the channel width, the smaller the data update interval threshold. Each ship is provided with a first interval threshold and a second interval threshold, the first interval threshold being smaller than the second interval threshold, and the ship update score is determined according to the first interval threshold, the second interval threshold and the update frequency of the AIS data of the ship. When the ship is in anchorage, the channel width where the ship is located becomes larger, and the second interval threshold is increased accordingly. When the ship is in a narrow waterway, the channel width where the ship is located becomes smaller, and the first interval threshold is decreased accordingly. The formula for determining the ship update frequency score according to the first interval threshold, the second interval threshold and the update frequency of the AIS data of the ship is as follows:

[0079] 10 seconds≤interval time≤30 seconds;

[0080] The initial value of the first interval threshold is 10 seconds, and the initial value of the second interval threshold is 30 seconds.

[0081] The interval time of AIS data feedback is determined according to the updating frequency of AIS data. When the interval time is less than or equal to a first interval threshold, the updating score corresponding to the ship is 100%; when the interval time is greater than a second interval threshold, the updating score corresponding to the ship is 0%; when the interval time is less than or equal to the second interval threshold and greater than the first interval threshold, the updating score is 100%-2% x (interval seconds-10).

[0082] The field of the ship static data and the ship dynamic data is checked to determine the formula of the data integrity score as follows:

[0083]

[0084] Among them, the mandatory field corresponding to the ship is determined by analyzing the field of the ship static data, the key field corresponding to the ship is determined by analyzing the field of the ship dynamic data, and the total number of fields corresponding to the AIS data of the ship is determined. By checking the missing fields of the mandatory field and the key field, at least one missing field number is determined.

[0085] Optionally, in the process of checking the missing fields in the mandatory field and the key field, the ship with a mandatory field missing rate greater than 5% is marked, and the ship is marked as a data incomplete state. The ship static data is completed by feedback information; AIS automatically associates radar or Vessel Traffic Service (VTS) to fill in the missing fields in the key field, and the corresponding ship is marked as a complete data state and recorded in the system.

[0086] The formula of the time synchronization score is determined according to the equipment time corresponding to the ship and the Coordinated Universal Time (UTC) as follows:

[0087] Time synchronization score = max(0, 100-20 x |Δt|);

[0088] Among them, Δt is the time difference between the time corresponding to the equipment clock of the ship and the Coordinated Universal Time, and the unit is second.

[0089] Optionally, the regional synchronization health degree is determined by the time difference between the equipment clock corresponding time of the plurality of ships in the same region and the world standard time, and the proportion of ships with a time difference between the equipment clock corresponding time and the world standard time greater than 3 seconds is counted. When the proportion of ships with a time difference greater than 3 seconds exceeds 10% of the total number of ships in the region, a "regional clock calibration suggestion" is triggered, and the ship clock in the region is calibrated. By setting the regional synchronization health degree, the amount of ship time synchronization operation is reduced, and the efficiency of ship time alignment is improved. The default value of the first time difference is 3 seconds, and the default value of the time alignment proportion threshold is 10%.

[0090] The first time difference is adjusted according to the focus index. When the focus index is for time synchronization, the first time difference is reduced based on the default value of the first time difference to improve the time alignment of the ships in the region, thereby meeting the time synchronization requirements of the plurality of ships.

[0091] The formula for determining signal stability according to the signal strength of AIS data is as follows:

[0092] H t =-∑P(x i )logP(x i );

[0093] Where H t is the entropy value, x i is the discretization region of signal strength, and P(x i ) is the probability of signal strength falling into the i-th discretization region.

[0094] For example, the signal strength of AIS data is in decibel-milliwatts (dBm), for example, the signal strength range is: -100 dBm (weak signal strength) to -60 dBm (strong signal strength), x1 is [-100, -90), x2 is [-90, -80), … x n is [-70, -60]. By counting the number of times the signal strength of AIS data falls into each discretization region within a predetermined time period (such as 1 hour), and determining the total number of AIS samples within the predetermined time period, the probability of signal strength falling into the i-th interval is determined by dividing the number of times the signal strength falls into each discretization region by the total number of AIS samples within the predetermined time period. For example, a ship collected 120 signal strength data in 1 hour, of which 30 fell into the first discretization region x1, 50 fell into the second discretization region x2, and 40 fell into the third discretization region x3, P(x1) = 30 / 120 = 0.25, P(x2) = 50 / 120 ≈ 0.42, P(x3) = 40 / 120 ≈ 0.33.

[0095] Furthermore, the stability level of the ship is determined based on the signal stability score. The ship's stability level includes a first signal stability level, a second signal stability level, and a third signal stability level. The visual identifier corresponding to the first signal stability level is a green stable waveform icon, the visual identifier corresponding to the second signal stability level is a yellow flashing icon, and the visual identifier corresponding to the third signal stability level is a red alarm triangle icon.

[0096] Each vessel is assigned a first entropy value and a second entropy value, with the first entropy value being less than the second entropy value. When the signal stability score is less than or equal to the first entropy value, the vessel's stability level is the first signal stability level, visually indicated by a green stable waveform icon; when the signal stability score is less than or equal to the second entropy value but greater than the first entropy value, the vessel's stability level is the second signal stability level, visually indicated by a yellow flashing icon; when the signal stability score is greater than the second entropy value, the vessel's stability level is the third signal stability level, visually indicated by a red warning triangle icon.

[0097] By determining signal stability using signal strength distribution entropy values ​​and displaying the ship's signal stability on the system interface in the form of visual indicators, ship managers or shipping companies can monitor ship signal stability in real time, improving the efficiency of anomaly detection and data quality assessment.

[0098] The formula for determining the ship's overall quality parameters based on dimensional weights and dimensional scores is as follows:

[0099]

[0100] Among them, dimension weights i This includes dimensional weights corresponding to the update frequency score, the integrity score, the time synchronization score, and the signal stability score. i The CQI (Comprehensive Quality Index) includes update frequency score, integrity score, time synchronization score, and signal stability score.

[0101] Understandably, by covering four core dimensions—update frequency, data integrity, time synchronization, and signal stability—the limitations of relying on a single indicator are eliminated, providing a more comprehensive AIS data quality assessment and improving the accuracy and reliability of the assessment results.

[0102] In some embodiments, optionally, such as Figure 8 As shown, after step S120: determining the ship's overall quality index based on dimensional weights and dimensional scores, the following steps are also included:

[0103] Step S1202: Using the electronic nautical chart as a base, divide the electronic nautical chart into regions according to a 1×1 nautical mile grid to determine multiple grid regions;

[0104] Step S1204: determining the average value of the comprehensive quality indexes of the plurality of ships in the grid area;

[0105] Step S1206: taking the average value as the grid comprehensive quality index score;

[0106] Step S1208: coloring the grid area according to the grid comprehensive quality index score to determine the global heat map.

[0107] In this embodiment, the AIS monitored sea area is divided into a plurality of uniform grid areas according to a 1x1 nautical mile grid based on an electronic sea chart, and the grid comprehensive quality index score of each grid area is determined by taking the average value of the CQI values of all ships in each grid area. The global heat map is determined by coloring the grid area according to the plurality of grid comprehensive quality index scores. The layer corresponding to the electronic sea chart is below the layer corresponding to the global heat map, that is, the global heat map displays the data quality distribution of the entire sea area by being overlaid on the electronic sea chart.

[0108] It can be understood that the global heat map can be used to visually display the comprehensive quality indexes of the plurality of ships in the sea area, reduce the workload of the user for quality assessment, help the user to quickly identify high-risk areas, and improve the efficiency of data quality assessment without checking each ship one by one.

[0109] Further, by setting the global heat map, the correspondence between the ship and the grid area is determined, and the plurality of ships and one grid area are associated, which lays the foundation for subsequent determination of abnormal ship data and early warning by the comprehensive quality index. By setting a 1x1 nautical mile grid, the electronic sea chart is discretized into a standard unit to provide a spatial reference for regional aggregation. The 1x1 nautical mile grid size ensures signal coverage density and improves the robustness of AIS data quality assessment. The global heat map is used as a guide to form a complete analysis chain of the global, regional and single ship, which improves the data processing efficiency and the intelligence of data quality assessment, and reduces the data processing workload. Moreover, by processing the comprehensive quality indexes of the plurality of ships in the grid area, the abnormal ship can be quickly located, and the response speed of the AIS data quality assessment is improved.

[0110] Specifically, the global heat map is provided with an interactive function, such as Figure 4As shown, the user displays the grid information by clicking on the grid area, the grid information includes grid label, grid CQI score and TOP3 low-score ship list of the grid, the grid label is #2218, the grid CQI score is 80, and the TOP3 low-score ship list includes ship 1, ship 2 and ship 3, wherein the score of ship 1 is 32, the MMSI is 413***123, and the ranking is first; the score of ship 2 is 38, the MMSI is 413***123, and the ranking is second; and the score of ship 3 is 44, the MMSI is 413***123, and the ranking is third.

[0111] Optionally, the grid area is a 2x2 nautical mile grid, a 2x3 grid or a non-rectangular grid, and the sea area can be uniformly divided by the grid area.

[0112] Optionally, the default 1x1 nautical mile grid can be adjusted according to the ship density of the sea area.

[0113] Optionally, in the global heat map, the ship data quality change (such as the CQI of a grid decreasing from 85 to 62) within 24 hours can be viewed by sliding the time axis.

[0114] Optionally, a ship number threshold of the grid area is set, when the total number of ships in the grid area is less than the ship number threshold of the grid area, only the grid area is marked and recorded as "insufficient data", and when the total number of ships in the grid area is greater than the ship number threshold of the grid area, the grid area is colored.

[0115] Optionally, the numerical value of the grid comprehensive quality index score is inversely proportional to the color gradient, and the color gradient is dark green to yellow to red.

[0116] Optionally, a regional index comparison dashboard is generated by the global heat map, and the dimension scores of different regions in the global heat map are compared in a visual form.

[0117] In one embodiment, optionally, as shown in Figure 9 After step S1208: coloring the grid area according to the grid comprehensive quality index score to determine the global heat map, it further includes:

[0118] Step S12082: determining the four-dimensional index score corresponding to the ship according to the plurality of dimension scores;

[0119] Step S12084: determining the historical trend curve and the abnormal event time axis according to the plurality of four-dimensional index scores;

[0120] Step S12086: determining the core panel corresponding to the ship according to the four-dimensional index score, the historical trend curve and the abnormal event time axis.

[0121] In this embodiment, the four-dimensional index score is determined based on the update frequency score, the integrity score, the time synchronization score and the signal stability score. The four-dimensional index score of the ship is continuously recorded within a preset time period, and a broken line graph is drawn according to the time axis to show the change trend of each dimension score, and a historical trend curve is determined. According to the time axis and the preset abnormal threshold corresponding to the multiple dimension scores, an abnormal event time axis is determined, and the abnormal events are arranged in chronological order. The four-dimensional index score, the historical trend curve and the abnormal event time axis are integrated into the core panel of the ship, wherein the four-dimensional index score is displayed in the form of a dashboard in the core panel.

[0122] It can be understood that the way of integrating the four-dimensional index score, the historical trend curve and the abnormal event time axis through the core panel improves the pertinence of data quality evaluation of a single ship. By setting the core panel, the data evaluation results are converted into intuitive charts and trend graphs, and the overall situation and change trend of the data quality can be visualized to help users make more accurate decisions and improve the data quality evaluation effect of users.

[0123] Specifically, the preset abnormal threshold is determined by an anomaly detection model. The anomaly detection model determines a normal data range by obtaining a historical comprehensive quality index of multiple ships. The normal data range includes: a normal frequency score data range corresponding to the update frequency score, a normal integrity score data range corresponding to the integrity score, a normal synchronization score data range corresponding to the time synchronization score, and a normal stability score data range corresponding to the signal stability score. When at least one dimension score in the four-dimensional index score of the ship exceeds the normal data range, or the data change amount of the ship exceeds the average value of the corresponding data change amount in the historical comprehensive quality index, it is determined that the ship has an anomaly, and the data is recorded in the time axis as an abnormal event time axis.

[0124] The real-time four-dimensional index score, as shown in Figure 6 The real-time four-dimensional index score includes the update frequency score (85 / 80), the data integrity score (90 / 87), the time synchronization score (85 / 80) and the signal stability score (88 / 88), wherein the score is displayed as the current score / average score of the same type of ship;

[0125] The historical trend curve, as shown in Figure 5 The horizontal axis represents time, and the vertical axis represents the historical CQI of the ship. The dashed line represents the average score of the same type of ship, which is 86.0;

[0126] The abnormal event time axis, as shown in Figure 7As shown, on 2023-08-20, 14:15, the signal entropy value suddenly increases to 3.8, on 2024-03-20, 14:15, the overall score quality suddenly drops to 80, and on 2024-06-20, 14:15, the signal stability reaches the average.

[0127] Optionally, the core panel can be customized by the user. The user can select at least one element from the four-dimensional index score, the historical trend curve, and the abnormal event timeline to form the core panel according to the data quality evaluation needs of the ship, so as to meet the individual needs of different users.

[0128] Optionally, the abnormal reason is determined according to the AIS data, the historical trend curve, and the abnormal event timeline, the abnormal reason includes the equipment model reason and the environmental influence reason, and the abnormal reason is marked. For example, the ship equipment model is determined according to the AIS data, the abnormal probability corresponding to the ship equipment model is determined according to the multiple abnormal event timelines, and the average value of the abnormal probability is determined according to the abnormal probability of multiple different ship equipment models. When the abnormal probability is greater than the average value of the abnormal probability, it is determined that the failure rate of the ship equipment model is high, and all ships of this ship equipment model are marked in the global heat map.

[0129] Optionally, the global heat map, the historical trend curve, and the abnormal reason are combined to generate a three-level visual analysis list.

[0130] When an abnormal event occurs on a ship, the low-quality ship data source can be located through the global heat map, that is, the grid area where the ship is located is located, and the abnormal event occurrence time is determined according to the historical trend curve, thereby improving the efficiency of abnormal detection.

[0131] Optionally, the processing mode of each quality event is recorded, the case library is determined according to the processing record, and when the system detects a similar pattern (such as "entropy value suddenly increases + zero speed") according to the field detection mode, the historical coping strategy is recommended according to the case library.

[0132] In one embodiment, optionally, the dimension weight corresponding to the update frequency score, the integrity score, the time synchronization score, and the signal stability score is determined according to the focus index and the multiple initial weights, including: the dimension weight corresponding to the update frequency score is determined according to the first focus index and the first initial weight; the dimension weight corresponding to the integrity score is determined according to the second focus index and the second initial weight; the dimension weight corresponding to the time synchronization score is determined according to the third focus index and the third initial weight; and the dimension weight corresponding to the signal stability score is determined according to the fourth focus index and the fourth initial weight.

[0133] In the embodiment, the dimension weight corresponding to the update frequency score, the dimension weight corresponding to the integrity score, the dimension weight corresponding to the time synchronization score and the dimension weight corresponding to the signal stability score are determined according to the emphasis index and the plurality of initial weights. The dimension weight and the ship type and the region type are adapted according to the weight requirement of the different types of ships in different regions, so as to improve the accuracy of the multi-dimensional AIS data quality evaluation.

[0134] Specifically, the emphasis index includes a first emphasis index, a second emphasis index, a third emphasis index and a fourth emphasis index, wherein the first emphasis index emphasizes the update frequency, the second emphasis index emphasizes the data integrity, the third emphasis index emphasizes the time synchronization, and the fourth emphasis index emphasizes the signal stability.

[0135] The initial weight includes a first initial weight, a second initial weight, a third initial weight and a fourth initial weight, wherein the first initial weight corresponds to the update frequency score, the second initial weight corresponds to the integrity score, the third initial weight corresponds to the time synchronization score, and the fourth initial weight corresponds to the signal stability score. The initial weight is a preset value.

[0136] At least one emphasis index corresponding to the ship is determined according to the ship type and the region operation attribute corresponding to each ship. Wherein, the corresponding relationship between the ship type and the emphasis index, the corresponding relationship between the region type and the emphasis index and the preset weight adjustment parameter corresponding to the emphasis index are obtained by preset. For example, when the ship type is a research ship, the corresponding emphasis index of the ship is determined to be the third emphasis index, and when the region type is a port operation area, the corresponding emphasis index of the port operation area is determined to be the first emphasis index. That is, when the research ship sails in the port operation area, the emphasis index of the ship is determined to be the first emphasis index and the third emphasis index, so as to meet the requirements of update frequency and time synchronization.

[0137] The dimension weight corresponding to the update frequency score is determined according to the first emphasis index and the first initial weight, that is, the first initial weight is adjusted by the preset weight adjustment parameter corresponding to the first emphasis index. For example, the preset weight adjustment parameter corresponding to the first emphasis index is +15%, the first initial weight is set to 30%, and the dimension weight corresponding to the update frequency score is 30%+15%, that is, the dimension weight corresponding to the update frequency score is 45%; the preset weight adjustment parameter corresponding to the third emphasis index is -10%, the third initial weight is set to 20%, and the dimension weight corresponding to the synchronization score is 20%-10%, that is, the dimension weight corresponding to the synchronization score is 10%.

[0138] Understandably, the dynamic weight is set on the basis of the initial weight, at least one emphasis index is determined through the ship type and the area operation attribute corresponding to each ship, and the initial weight is updated through the at least one emphasis index, so as to meet the navigation requirements of different types of ships in different sea areas and improve the accuracy of AIS data quality evaluation.

[0139] Optionally, the preset weight adjustment parameter, the area operation attribute and the ship type are in a binding relationship, that is, each area operation attribute corresponds to a preset weight adjustment parameter of the area type, and each ship type corresponds to a preset weight adjustment parameter of the ship type.

[0140] In one embodiment, optionally, the comprehensive quality index of the ship is determined according to the dimension weight and the dimension score, including: determining an update frequency quality index according to the dimension weight corresponding to the update frequency score and the update frequency score; determining an integrity quality index according to the dimension weight corresponding to the integrity score and the integrity score; determining a time synchronization quality index according to the dimension weight corresponding to the time synchronization score and the time synchronization score; determining a signal stability quality index according to the dimension weight corresponding to the signal stability score and the signal stability score; and determining a comprehensive quality index according to the update frequency quality index, the integrity quality index, the time synchronization quality index and the signal stability quality index.

[0141] In this embodiment, each dimension score is multiplied by the adjusted dimension weight to generate a quality index of the dimension, and the quality index includes an update frequency quality index, an integrity quality index, a signal stability quality index and a time synchronization quality index. The update frequency quality index, the integrity quality index, the signal stability quality index and the time synchronization quality index are added to determine the final comprehensive quality index.

[0142] Understandably, the scores of the update frequency dimension, the integrity dimension, the time synchronization dimension and the signal stability dimension are integrated into a single index (CQI) through weighted summation, so as to realize comprehensive evaluation of AIS data of a single ship and provide reliable data support for subsequent abnormal signal evaluation.

[0143] Specifically, the update frequency quality index = the update frequency score x the dimension weight corresponding to the update frequency score; the integrity quality index = the integrity score x the dimension weight corresponding to the integrity score; the time synchronization quality index = the time synchronization score x the dimension weight corresponding to the time synchronization score; the signal stability quality index = the signal stability score x the dimension weight corresponding to the signal stability score; and the comprehensive quality index = the update frequency quality index + the integrity quality index + the time synchronization quality index + the signal stability quality index.

[0144] In one embodiment, optionally, as Figure 10As shown, in step S1208: after determining the global heat map according to the grid region coloring based on the grid synthesis quality index score, the method further comprises:

[0145] Step S200: determining at least one inferior ship according to the synthesis quality index of the plurality of ships in the grid region;

[0146] Step S202: obtaining a quality score threshold;

[0147] Step S204: when at least one dimension score of the ship is less than the quality score threshold, and the ship is an inferior ship, determining that the data quality type of the ship is the first type.

[0148] In this embodiment, on the basis of dividing the grid region through the global heat map, the synthesis quality index of all ships in the grid region is summarized to determine at least one inferior ship in the region. At least one of the four dimension scores of the inferior ship is less than the quality score threshold, and on the basis of determining that the ship is an inferior ship, the data quality type of the ship is determined to be the first type. The AIS data quality assessment result of the ship does not meet the data quality requirement, and the ship needs to be prioritized for maintenance and investigation. The quality score threshold is the average value of the sum of the dimension scores of all ships in the region.

[0149] It can be understood that the data quality of the ship is determined through the double conditions of grid region screening and dimension threshold determination, which further improves the accuracy and reliability of the ship AIS data quality assessment. Moreover, through the analysis of the synthesis quality index of all ships in different grid regions, the parallel analysis of the overall AIS data quality of the region and the AIS data quality of a single ship is performed, so that the data quality assessment of the ship relies on the overall data quality of the region, improves the accuracy of the data quality assessment of the ship in different sea areas, and meets the needs of different sea areas.

[0150] Optionally, in a case where the first type of ship in the plurality of grid regions is determined, the dimension scores of all first type of ships are obtained, and the dimension scores are sorted from low to high to determine the maintenance and investigation priority. That is, the smaller the dimension score of the ship, the higher the maintenance and investigation priority corresponding to the ship. By setting the maintenance and investigation priority, the plurality of first type of ships are sorted to guide the directional deployment of operation and maintenance resources and improve the operation and maintenance efficiency.

[0151] Optionally, the synthesis quality index of all ships in the grid region is determined, all synthesis quality indexes are sorted from high to low to determine a quality index sequence, and the ships located at the last or several last positions in the quality index sequence are determined as inferior ships.

[0152] In one embodiment, optionally, as Figure 11As shown, in step S1208: coloring the grid area according to the grid synthesis quality index score, after determining the global heat map, further includes:

[0153] Step S206: determining an analysis time period;

[0154] Step S208: determining a plurality of synthesis quality indexes of the ship in the analysis time period;

[0155] Step S210: determining an AIS data quality change parameter corresponding to the ship according to the plurality of synthesis quality indexes in the analysis time period;

[0156] Step S212: obtaining a data quality change threshold;

[0157] Step S214: determining that the data quality type of the ship is the second type when the AIS data quality change parameter is greater than the data quality change threshold.

[0158] In this embodiment, by determining a plurality of synthesis quality indexes of the ship in a time period, an AIS data quality change parameter of the ship is determined, the AIS data quality change parameter is determined according to the plurality of synthesis quality indexes of the ship, specifically, the AIS data quality change parameter is the slope of the analysis time period fitted by the plurality of synthesis quality indexes of the ship, that is, the change of the synthesis quality index of the ship in the time period, the symbol of the AIS data quality change parameter is negative, indicating that the data quality of the ship is in a declining state. The analysis time period and the data quality change threshold are preset values, when the value corresponding to the AIS data quality change parameter is greater than the data quality change threshold, it is determined that the data quality of the ship is in a continuous deterioration state, and the ship needs to be prompted for preventive maintenance, that is, the data quality type of the ship is the second type.

[0159] It can be understood that by associating and analyzing the synthesis quality index and the time period, the data quality change of the ship in the continuous time period is determined, the ship needing preventive maintenance is determined, the ship of the second type is determined to judge the ship with continuously decreasing synthesis quality index, the ship with continuously decreasing synthesis quality index is repaired in advance, accidents caused by data quality deterioration are avoided, abnormal ships are warned, and the safety of ship navigation is improved.

[0160] Optionally, the analysis time period is a time window divided according to day granularity, for example, the past 3 days or the past 7 days.

[0161] Optionally, the analysis time period can be determined according to the weather condition, when the weather condition corresponding to the grid area is good, the time corresponding to the analysis time period is increased; when the weather condition corresponding to the grid area is bad, the time corresponding to the analysis time period is decreased.

[0162] Optionally, the data quality change threshold is positively correlated with the average of the comprehensive quality index of all ships in the grid area.

[0163] When the average of the comprehensive quality index of all ships in the grid area increases, the data quality change threshold is increased by a preset value, and the increase amplitude is equal to the change rate of the comprehensive quality index of all ships in the grid area; when the average of the comprehensive quality index of all ships in the grid area decreases, the data quality change threshold is decreased by a preset value, and the increase amplitude is equal to the change rate of the comprehensive quality index of all ships in the grid area.

[0164] Optionally, the first type of ship is the top 10 worst ships in the area.

[0165] Optionally, the low-quality ship list supports export to a Microsoft Office Excel (Excel) / Portable Document Format (PDF) format file and contains rectification suggestions (such as “replace antenna position” and “upgrade firmware version”).

[0166] In one embodiment, as shown in Figure 12 After step S12086: determining the core panel corresponding to the ship according to the four-dimensional index score, the historical trend curve and the abnormal event timeline, the method further comprises:

[0167] Step S300: determining historical AIS data of each grid area in the global heat map according to a plurality of historical trend curves;

[0168] Step S302: determining a historical average corresponding to the grid comprehensive quality index score of the grid area according to the historical AIS data;

[0169] Step S304: determining that the early warning type is a first early warning type when the grid comprehensive quality index score of the grid area is less than the historical average, or when at least one dimension score of a ship in the grid area is less than a quality score threshold.

[0170] In this embodiment, for each grid area, the historical AIS data corresponding to the area is determined in combination with the historical trend curve, the historical AIS data including the historical comprehensive quality index of all ships in the grid area, the ship and the area are determined as the first warning type when the grid comprehensive quality index score of the grid area is less than the average value of the historical AIS data, or at least one dimension score of a single ship in the area is less than the quality score threshold, and the ship and the area of the first warning type are marked with yellow warning in the electronic chart. The warning information of the ship and the area is pushed through the platform message center. The grid area and the single ship are associated and analyzed, the AIS data of all ships in a specific area is analyzed by summarizing, the regional data quality problem is quickly identified, and the efficiency of data quality evaluation is improved.

[0171] It can be understood that the historical average value corresponding to the grid area is taken as the dynamic reference, the fixed threshold value cannot adapt to the characteristics of the area, the average value of the historical AIS data of the grid area is taken as the threshold value, the pertinence to different areas in the data quality evaluation process is improved, the false alarm is reduced, and the warning accuracy is improved.

[0172] Optionally, when the first warning type is triggered, the historical data and the abnormal event timeline are quickly associated to determine the historical abnormal event of the ship or the area, and the determination result is displayed on the push page.

[0173] In one embodiment, as shown in Figure 13 In one embodiment, as shown in

[0174] Step S306: determining the first warning parameter and the second warning parameter;

[0175] Step S308: when the comprehensive quality index score of the ship in the grid area is less than the first warning parameter or the grid comprehensive quality index score of the grid area is less than the second warning parameter, determining that the warning type is the second warning type.

[0176] In this embodiment, the first early warning parameter and the second early warning parameter are determined, the first early warning parameter is less than the second early warning parameter, the first early warning parameter is used to determine the data quality corresponding to the ship comprehensive quality index, and the second early warning parameter is used to determine the data quality corresponding to the grid comprehensive quality index score of the grid area. Wherein, the first early warning parameter is greater than the quality score threshold, and the second early warning parameter is greater than the quality score threshold. The first early warning parameter and the second early warning parameter are both preset values. When the comprehensive quality score index of the ship in the area is less than the first early warning parameter or the grid comprehensive quality index score of the grid area is less than the second early warning parameter, the second early warning type is determined, and the ship and the area of the second early warning type are marked with red color in the electronic chart. The early warning information of the ship and the area is pushed through the combination of platform pop-up window, short message and email. The grid area and the single ship are associated and analyzed, the AIS data of all ships in a specific area are summarized and analyzed, the abnormal data quality of the area or the abnormal data quality of the single ship is alarmed, and the safety risk caused by the data quality problem is reduced.

[0177] It can be understood that by setting the first early warning parameter less than the second early warning parameter, the first early warning parameter is used to determine the data quality corresponding to the ship comprehensive quality index, and the second early warning parameter is used to determine the data quality corresponding to the grid comprehensive quality index score of the grid area. The overall data quality requirement of the area is higher than the single ship quality requirement. Wherein, the first early warning parameter and the second early warning parameter are preset values. On this basis, the risk classification management of the ship and the grid area is realized, the excessive alarm caused by the single threshold is avoided, the operation and maintenance resources are reasonably allocated, and the data quality analysis efficiency is improved.

[0178] Exemplarily, the first early warning parameter is 60, and the second early warning parameter is 70.

[0179] Optionally, the first early warning parameter and the second early warning parameter can be automatically adjusted according to the weather condition corresponding to the grid area. When the weather condition is sunny, the first early warning parameter and the second early warning parameter are less than the preset value; when the weather condition is thunderstorm, the first early warning parameter and the second early warning parameter are greater than the preset value.

[0180] Further, by visualizing the first early warning type and the second early warning type in the electronic chart, the user can quickly locate the data quality abnormal area, and improve the efficiency of the user to find the data problem.

[0181] Optionally, the early warning area / ship is marked on the electronic chart, and the same type of ship comparison data (such as "the average CQI of the same type of ship is 82 points") is displayed by clicking.

[0182] Optionally, after triggering the first pre-warning type or the second pre-warning type, the system automatically generates a report including the processing details, and the system automatically associates the report with the core panel and the global heat map, so that when the user views the core panel, the user can view the processing details of each ship in the secondary window of the core panel or the secondary window of the global heat map.

[0183] Optionally, the processing details in the report are displayed in the form of an abnormal event timeline.

[0184] Optionally, after triggering the first pre-warning type or the second pre-warning type, the system automatically generates a report including the improvement suggestions for the grid area corresponding to the pre-warning, and the improvement suggestions include: equipment upgrade, base station expansion, and operation and maintenance inspection. For example, the equipment upgrade, 32% of the low-score ships use old AIS terminals (models before 2015), and the old AIS terminals are upgraded; the base station expansion, the signal coverage rate of the southwest grid is only 75% (the demand is ≥ 90%), and the base station is expanded to make the signal coverage rate of the southwest grid meet the data quality evaluation demand, i.e. the coverage rate is ≥ 90%; the operation and maintenance inspection, the peak value of the synchronization deviation needs to be checked every week at 3 a.m.

[0185] Optionally, the AIS data and the pre-warning records are input into an eXtreme Gradient Boosting (XGBoost) model at a monthly frequency to determine the new data distribution characteristics; after the user provides a correction feedback on the new data distribution characteristics, the XGBoost scoring model after the correction feedback is used to optimize the threshold settings in the AIS data quality evaluation.

[0186] In one specific embodiment, the AIS data quality evaluation method includes the following specific steps:

[0187] Step 1: Construction and quantification of a multi-dimensional dynamic quality index system

[0188] 1. Core quality dimension definition and dynamic threshold setting

[0189] (1) Update frequency (initial weight is 30%);

[0190] The quantification rules are as follows:

[0191] 10 seconds≤interval time≤30;

[0192] Wherein, the interval threshold is automatically adjusted according to the navigation area corresponding to the ship, the initial value of the first interval threshold is 10 seconds, and the initial value of the second interval threshold is 30 seconds, and the update score is the update frequency score.

[0193] The AIS data update interval time is determined according to the AIS data update frequency, when the interval time is less than or equal to a first interval threshold, the update score corresponding to the ship is 100%; when the interval time is greater than a second interval threshold, the update score corresponding to the ship is 0%; when the interval time is less than or equal to the second interval threshold and greater than the first interval threshold, the update score is 100%-2% (interval seconds-10).

[0194] Exemplarily, when the navigation area is an anchorage, the second interval threshold is relaxed to 60 seconds, that is, when the AIS data update frequency interval exceeds 60 seconds, the update score is determined to be 0%; when the navigation area is a narrow waterway, the first interval threshold is tightened to 5 seconds, that is, when the AIS data update frequency interval is less than 5 seconds, the update score is determined to be 100%.

[0195] Dynamic board setting: determine the regional update frequency distribution heat map, display the update frequency compliance rate by color gradient, support switching by hour / day granularity.

[0196] Optionally, the update frequency compliance rate is displayed by a color gradient from dark green to red.

[0197] When the update score of the ship exceeds a preset compliance score, it is determined that the update frequency of the ship is compliant.

[0198] Exemplarily, the preset compliance score is 60%, and the update score of the ship is 80%, so the update frequency of the ship is compliant.

[0199] (2) Data integrity (initial weight is 25%);

[0200] The detection of the missing fields of the ship includes the detection of the missing fields in the mandatory fields and the key fields, wherein:

[0201] The mandatory fields are associated with 24 AIS standards, corresponding to the static data of the ship, and the ship with a mandatory field missing rate greater than 5% is marked as "incomplete data";

[0202] The key fields are associated with dynamic data of the ship, for example, fields corresponding to the position and speed of the ship, the key fields of the ship are automatically associated with radar / VTS data, the missing fields are filled by the radar / VTS data, and the ship is marked as "complete data".

[0203] The scoring formula of data integrity is as follows:

[0204]

[0205] Wherein, the total number of fields is from the AIS data of the ship, and the number of missing fields is from the mandatory fields and the key fields.

[0206] (3) Time synchronization (initial weight 20%);

[0207] The synchronization score is determined according to the clock deviation calculation, and the formula is as follows:

[0208] Synchronization score = max (0, 100-20x|Δt|);

[0209] Wherein, Δt is the time difference between the equipment clock corresponding time of the ship and the world standard time, in seconds.

[0210] Further, the regional synchronization health degree is set, and the proportion of ships with a time difference between the equipment clock corresponding time and the world standard time greater than 3 seconds is counted. When the proportion of ships with a time difference greater than 3 seconds exceeds 10% of the total number of ships in the region, the "regional clock calibration suggestion" is triggered, and the clock of the ship in the region is calibrated.

[0211] (4) Signal stability (initial weight 25%);

[0212] The entropy fluctuation of the ship is detected, and the formula is as follows:

[0213] H t =-∑P(x i )logP(x i );

[0214] Wherein, H t is the entropy value, which is the signal stability score, x i is the discretization region of signal strength, and P(x i ) is the probability of signal strength falling into the i-th discretization region.

[0215] According to the entropy value, the signal stability of the ship is classified:

[0216] Table 1

[0217] Rank Entropy value range Visual identifier Good H t ≤1.5]]> Green stable waveform icon Medium 1.5 < H t ≤ 3 Yellow flashing icon Poor H t >3]]> Red alarm triangle icon

[0218] As shown in Table 1, when the entropy value H t ≤1.5, the signal stability of the ship is excellent (the first signal stability level), and the corresponding visual identifier is a green stable waveform icon; when the entropy value range is 1.5 t ≤3, the signal stability of the ship is medium (the second signal stability level), and the corresponding visual identifier is a yellow flashing icon; when the entropy value range is H t >3, the signal stability of the ship is poor (the third signal stability level), and the corresponding visual identifier is a red alarm triangle icon.

[0219] 2. Dynamic weight and scene adaptation:

[0220] Region type adaptation:

[0221] Table 2

[0222]

[0223] As shown in Table 2, when the region type is a port operation area, at this time the focus index is for the update frequency, and the weight corresponding to the update frequency is adjusted accordingly, which is increased by 15% on the basis of the initial weight. Moreover, the first interval threshold is compressed to 8 seconds; when the region type is an international shipping lane, at this time the focus index is for time synchronization, and in the process of setting the region synchronization health degree, the proportion of ships with a time difference between the corresponding time of the equipment clock in the region and the world standard time greater than 2 seconds is counted. When the proportion of ships with a time difference greater than 2 seconds exceeds 10% of the total number of ships in the region, a "region clock calibration suggestion" is triggered, and the ship clock in the region is calibrated; when the region type is a fishing area, at this time the focus index is for signal stability, and the entropy value range is relaxed to 4.0, i.e. when H t > 4, the signal stability of the ship is poor, and the corresponding visual identifier is a red warning triangle icon.

[0224] Ship type adaptation: when the ship type is a container ship, the integrity weight corresponding to the ship is increased by 10% on the basis of the initial weight, because the ship frequently needs to dock and requires high data completeness; when the ship type is a research ship, the synchronization weight corresponding to the ship is reduced by 10% on the basis of the initial weight, because the research ship allows temporary shutdown of equipment.

[0225] Step two: region-ship double-layer quality analysis and visualization:

[0226] 1. Region-level quality panoramic analysis:

[0227] A global heat map is set, which is based on an electronic chart and displays the comprehensive quality index by coloring 1x1 nautical mile grid, and the formula is as follows:

[0228]

[0229] Among them, the dimension weight i includes the dimension weight corresponding to the update frequency score, the dimension weight corresponding to the integrity score, the dimension weight corresponding to the time synchronization score, and the dimension weight corresponding to the signal stability score, and the dimension score i includes the update frequency score, the integrity score, the time synchronization score, and the signal stability score.

[0230] The global heat map is correspondingly provided with an interactive function, such as Figure 4As shown in FIG. 6, the grid display TOP3 low-score ship list, the grid label is #2218, the grid CQI score is 80, and the TOP3 low-score ship list includes ship 1, ship 2 and ship 3. The score of ship 1 is 32, the MMSI is 413***123, and the ranking is first. The score of ship 2 is 38, the MMSI is 413***123, and the ranking is second. The score of ship 3 is 44, the MMSI is 413***123, and the ranking is third.

[0231] In addition, in the global heat map, the ship data quality change in 24 hours (such as the CQI of a grid from 85 to 62) can be viewed by sliding the time axis.

[0232] Set regional index comparison board:

[0233] Table 3

[0234]

[0235] As shown in Table 3, region A is a channel, the corresponding update frequency is 98%, the visualization form is a double column chart + industry average reference line, the average synchronization deviation is 1.2 seconds, and the visualization form is a radar chart superimposed manner.

[0236] Region B is an anchorage, and the corresponding update frequency is 72%. The visualization form is a double column chart + industry average reference line, the average synchronization deviation is 4.8 seconds, and the visualization form is a radar chart superimposed manner.

[0237] The radar chart is obtained by a radar system.

[0238] 2. Ship level depth evaluation and traceability:

[0239] Set up a single ship quality archive as the core panel of the ship display AIS data, and the single ship quality archive includes:

[0240] Real-time four-dimensional index score (in the form of a dashboard), such as Figure 6 As shown in FIG. 8, the real-time four-dimensional index score includes an update frequency score (85 / 80), a data integrity score (90 / 87), a time synchronization score (85 / 80), and a signal stability score (88 / 88), wherein the score is displayed as the current score / average score of the same type of ship.

[0241] Historical trend curve (comparable to the average of the same type of ship), such as Figure 5 As shown in FIG. 9, the horizontal axis represents time, and the vertical axis represents the historical CQI of the ship. The dashed line in the figure represents the average score of the same type of ship, and the average score of the same type of ship is 86.0.

[0242] Abnormal event timeline, such as Figure 7As shown, on 2023-08-20, 14:15, the signal entropy value suddenly increased to 3.8, on 2024-03-20, 14:15, the overall score quality dropped to 80, and on 2024-06-20, 14:15, the signal stability reached the average.

[0243] Root cause speculation: automatically associate device models (such as "XX model terminal failure rate is higher"); environmental factors (such as "the regional satellite signal strength decreased by 30% on the day").

[0244] Determine the low-quality ship list and dynamically generate two types of lists:

[0245] Table 4

[0246]

[0247] As shown in Table 4, the list types include the worst ship in the region (the first type), which corresponds to the screening condition of CQI ranking last and at least one indicator < 50 points, and the typical application scenario is priority repair investigation; continuously deteriorating ships (the second type), which correspond to the screening condition of a score drop of > 20% for 3 consecutive days, and the typical application scenario is preventive maintenance prompt.

[0248] Optionally, the first type of ship is the top 10 worst ships in the region.

[0249] The low-quality ship list supports export to Excel / PDF format files and includes rectification recommendations (such as "replace antenna position" and "upgrade firmware version").

[0250] 3. Intelligent early warning and visual push:

[0251] The trigger condition for red alert level is single ship CQI < 60 points or regional CQI < 70 points, and the push method for red alert is SMS, platform pop-up window, and email synchronous push;

[0252] The trigger condition for yellow alert level is single ship single indicator < 50 points or regional indicator lower than historical average, and the push method for yellow alert is platform message center push.

[0253] The threshold trigger rules are shown in the following table:

[0254] Table 5

[0255]

[0256] Optionally, according to the normal distribution characteristics, the triggering condition of the yellow pre-warning level is that the single-ship single-index is less than 50 points or the regional index is lower than the historical average + 2σ, wherein σ is the standard deviation for measuring the dispersion degree of historical data, when the regional index is lower than the historical average + 2σ, the data quality in the regional grid is normal; when the regional index exceeds the historical average + 2σ, the data quality in the regional grid is abnormal, and the yellow pre-warning is determined.

[0257] A visual pre-warning map is set, the pre-warning area / ship is marked on the electronic chart, and the comparison data of the same type of ship (such as “the average CQI of the same type of ship is 82 points”) is displayed by clicking.

[0258] Step three: data-driven quality optimization and decision support:

[0259] 1. Quality root cause analysis and improvement suggestions:

[0260] Correlation analysis through pattern mining engine:

[0261] Low-quality ship clustering (such as “80% of CQI < 60 ships use a certain manufacturer's equipment”);

[0262] Time regularity (such as “the regional signal stability decreases by 40% from 02:00 to 04:00 UTC every day”).

[0263] Automatic generation of reports, and the quality improvement suggestions for region X are as follows:

[0264] Equipment upgrade: 32% of low-score ships use old AIS terminals (models before 2015); base station expansion: the signal coverage rate of the southwest grid is only 75% (demand ≥ 90%); operation and maintenance inspection: the peak value of synchronization deviation needs to be checked in the early morning every week.

[0265] 2. Dynamic knowledge base and adaptive optimization:

[0266] Case library driven iteration: record the processing scheme of each quality event, and build a case library of 3000+; when similar patterns (such as “entropy value sudden increase + zero speed”) are detected, automatically recommend historical coping strategies.

[0267] Model online learning: update the XGBoost scoring model every month, and include new data distribution characteristics; user feedback on evaluation results (such as “mistakenly marking a parked ship as abnormal”) is automatically used to optimize the threshold logic.

[0268] In one specific embodiment, optionally in a Singapore Strait deployment, the system found that the grid update frequency score on the east side of the Strait dropped to 58% (industry safety baseline 75%), further pinpointing 12 bulk carriers with update intervals over 40 seconds. This was traced to a local base station failure, which was fixed and the CQI in that area rose back to 89%. The maritime authorities used this to optimize the base station layout, and the regional data availability improved by 33% and the ship trajectory prediction accuracy improved by 28%.

[0269] As Figure 2 shown in the drawings, the embodiments of the present application also provide an AIS data quality evaluation device 900, comprising:

[0270] a data acquisition module 902, configured to acquire AIS data of a plurality of ships, the AIS data comprising ship static data, ship dynamic data and ship type; determine a sea area type corresponding to each ship, the sea area type comprising regional operation attribute and regional waterway attribute;

[0271] a frequency determination module 904, configured to determine a data update interval threshold corresponding to each ship according to the regional waterway attribute; determine an update frequency score according to the update frequency of the acquired AIS data of the ship and the data update interval threshold;

[0272] a field module 906, configured to determine a data integrity score according to the ship static data and the ship dynamic data;

[0273] a time module 908, configured to determine a device time corresponding to the ship, and determine a time synchronization score according to the device time and the world standard time;

[0274] a signal determination module 910, configured to determine a signal stability score according to the signal strength of the AIS data;

[0275] a dynamic weight module 912, configured to determine an initial weight, the initial weight comprising a first initial weight corresponding to the new frequency score, a second initial weight corresponding to the integrity score, a third initial weight corresponding to the time synchronization score, and a fourth initial weight corresponding to the signal stability score; determine at least one emphasis index according to the ship type and the regional operation attribute corresponding to each ship, the emphasis index comprising a first emphasis index, a second emphasis index, a third emphasis index and a fourth emphasis index; determine a dimension weight corresponding to the update frequency score, the integrity score, the time synchronization score and the signal stability score according to the emphasis index and the plurality of initial weights;

[0276] a quality evaluation module 914, configured to determine a comprehensive quality index of the ship according to the dimension weight and the dimension score, the dimension score comprising the update frequency score, the integrity score, the time synchronization score and the signal stability score.

[0277] According to the AIS data quality evaluation device and method provided in the application, a multi-dimensional dynamic quality index system is constructed from four dimensions of data update frequency, data integrity, time synchronization and signal stability, the update frequency, data integrity, time synchronization and signal stability of AIS data are comprehensively evaluated, and the AIS data quality is comprehensively controlled. On this basis, the corresponding relationship between the ship and the grid area is determined by setting a global heat map, a plurality of ships and a grid area are associated, the subsequent determination of abnormal ship data and early warning through the comprehensive quality index are prepared, the global heat map is used as a guide to form a complete analysis chain of the global, regional and single ship, the data processing efficiency and the intelligence of the data quality evaluation are improved, and the data processing workload is reduced. Moreover, the abnormal ship can be quickly positioned through the grid area processing of the comprehensive quality index of a plurality of ships, and the response speed of the AIS data quality evaluation is improved.

[0278] As Figure 3 shown, the application also provides an electronic device 1000, which comprises a processor 1110, a memory 1109, a program or instruction stored in the memory 1109 and executable on the processor 1110. The program or instruction is executed by the processor 1110 to realize the processes of the embodiments of the AIS data quality evaluation method described above, and the same technical effects can be achieved. To avoid repetition, details are not described here.

[0279] Optionally, the processor 1110 is configured to acquire AIS data of a plurality of ships, wherein the AIS data comprises ship static data, ship dynamic data and ship type; and determine a sea area type corresponding to each ship, wherein the sea area type comprises a regional operation attribute and a regional waterway attribute.

[0280] Optionally, the processor 1110 is further configured to determine a data update interval threshold corresponding to each ship according to the regional waterway attribute; and determine an update frequency score according to an update frequency of the AIS data of the ship and the data update interval threshold.

[0281] Optionally, the processor 1110 is further configured to determine a data integrity score according to the ship static data and the ship dynamic data.

[0282] Optionally, the processor 1110 is further configured to determine a device time corresponding to the ship, and determine a time synchronization score according to the device time and a world standard time.

[0283] Optionally, the processor 1110 is further configured to determine a signal stability score according to a signal strength of the AIS data.

[0284] Optionally, the processor 1110 is further configured to determine initial weights, the initial weights comprising a first initial weight corresponding to the update frequency score, a second initial weight corresponding to the integrity score, a third initial weight corresponding to the time synchronization score, and a fourth initial weight corresponding to the signal stability score; determine at least one emphasis index according to the ship type and the regional operation attribute corresponding to each of the ships, the emphasis index comprising a first emphasis index, a second emphasis index, a third emphasis index, and a fourth emphasis index; and determine dimension weights corresponding to the update frequency score, the integrity score, the time synchronization score, and the signal stability score according to the emphasis index and the initial weights.

[0285] Optionally, the processor 1110 is further configured to determine a comprehensive quality index of the ship according to the dimension weights and dimension scores, the dimension scores comprising the update frequency score, the integrity score, the time synchronization score, and the signal stability score.

[0286] The memory 1109 can be used to store software programs and various data. The memory 1109 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), etc. In addition, the memory 1109 can include a volatile memory or a non-volatile memory, or the memory 1109 can include both volatile and non-volatile memories. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 1109 in the embodiments of the present application includes but is not limited to these and any other suitable types of memories.

[0287] The embodiments of the present application also provide a readable storage medium, and the readable storage medium stores programs or instructions, the programs or instructions are executed by a processor to realize the processes of the AIS data quality evaluation method embodiments and achieve the same technical effects. To avoid repetition, details are not described here. In addition, the readable storage medium improves the data storage capacity and data processing speed of the AIS data quality evaluation method in the present application.

[0288] The readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media, or electrical signals transmitted through a wire cable or optical cable, and the like.

[0289] The processor is a processor in the electronic device in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like.

[0290] The chip provided by the embodiments of the present application includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run programs or instructions to implement the processes of the above AIS data quality evaluation method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein. In addition, the chip improves the data processing speed of the AIS data quality evaluation method in the present application.

[0291] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-level chip, a system chip, a chip system, or a system-on-chip, etc.

[0292] In the present application, the terms "first", "second", "third" are only used for descriptive purposes and should not be construed as indicating or implying relative importance. The term "multiple" refers to two or more, unless otherwise explicitly limited. The terms "mounting", "connecting", "connecting", "fixing" and the like should be understood in a broad sense. For example, "connecting" can be fixed connection, or detachable connection, or integral connection; "connecting" can be direct connection, or indirect connection through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0293] In the description of the application, it should be understood that the terms "upper", "lower", "left", "right", "front", "rear", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the application and simplifying the description, and do not indicate or imply that the device or unit referred to must have a particular direction, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the application.

[0294] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "a specific embodiment" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description 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.

[0295] The above is only the preferred embodiment of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An AIS data quality assessment method, characterized by, The method comprises: acquiring AIS data of a plurality of ships, the AIS data comprising ship static data, ship dynamic data and ship type; determining a sea area type corresponding to each of the ships, the sea area type comprising regional operation attribute and regional waterway attribute; determining a data update interval threshold corresponding to each of the ships according to the regional waterway attribute; determining an update frequency score according to the update frequency of the AIS data of the ship and the data update interval threshold; determining a data integrity score according to the ship static data and ship dynamic data; determining equipment time corresponding to the ship, and determining a time synchronization score according to the equipment time and world standard time; determining a signal stability score according to the signal strength of the AIS data; determining initial weights, the initial weights comprising a first initial weight corresponding to the update frequency score, a second initial weight corresponding to the integrity score, a third initial weight corresponding to the time synchronization score, and a fourth initial weight corresponding to the signal stability score; determining at least one emphasis index according to the ship type and the regional operation attribute corresponding to each of the ships, the emphasis index comprising a first emphasis index, a second emphasis index, a third emphasis index and a fourth emphasis index; determining dimension weights corresponding to the update frequency score, the integrity score, the time synchronization score and the signal stability score according to the emphasis index and a plurality of the initial weights; determining a comprehensive quality index of the ship according to the dimension weights and dimension scores, the dimension scores comprising the update frequency score, the integrity score, the time synchronization score and the signal stability score; after the determining of the comprehensive quality index of the ship according to the dimension weights and dimension scores, the AIS data quality evaluation method further comprises: dividing the electronic sea chart into a plurality of grid areas according to a 1x1 nautical mile grid based on the electronic sea chart; determining the average value of the comprehensive quality index of a plurality of the ships in the grid area; taking the average value as a grid comprehensive quality index score; coloring the grid area according to the grid comprehensive quality index score to determine a global heat map.

2. The AIS data quality assessment method of claim 1, wherein, after the determining of the global heat map, the AIS data quality evaluation method further comprises: determining a four-dimensional index score corresponding to the ship according to a plurality of dimension scores; determining a historical trend curve and an abnormal event time axis according to a plurality of the four-dimensional index scores; determining a core panel corresponding to the ship according to the four-dimensional index score, the historical trend curve and the abnormal event time axis.

3. The AIS data quality assessment method of claim 1, wherein, the determining of the dimension weights corresponding to the update frequency score, the integrity score, the time synchronization score and the signal stability score according to the emphasis index and a plurality of the initial weights comprises: determining the dimension weight corresponding to the update frequency score according to the first emphasis index and the first initial weight; determining the dimension weight corresponding to the integrity score according to the second emphasis index and the second initial weight; determining the dimension weight corresponding to the time synchronization score according to the third emphasis index and the third initial weight; determining the dimension weight corresponding to the signal stability score according to the fourth emphasis index and the fourth initial weight.

4. The AIS data quality assessment method of claim 3, wherein, determining the comprehensive quality index of the ship according to the dimension weight and the dimension score, comprising: determining an update frequency quality index according to the dimension weight and the update frequency score corresponding to the update frequency score; determining an integrity quality index according to the dimension weight and the integrity score corresponding to the integrity score; determining a time synchronization quality index according to the dimension weight and the time synchronization score corresponding to the time synchronization score; determining a signal stability quality index according to the dimension weight and the signal stability score corresponding to the signal stability score; determining a comprehensive quality index according to the update frequency quality index, the integrity quality index, the time synchronization quality index and the signal stability quality index.

5. The AIS data quality assessment method of claim 1, wherein, The AIS data quality evaluation method further comprises: determining at least one poor state ship according to the comprehensive quality index of a plurality of ships in the grid area; obtaining a quality score threshold; when at least one of the dimension scores of the ship is less than the quality score threshold, and the ship is the poor state ship, determining that the data quality type of the ship is a first type.

6. The AIS data quality assessment method of claim 5, wherein, The AIS data quality evaluation method further comprises: determining an analysis time period; determining a plurality of comprehensive quality indexes of the ship in the analysis time period; determining an AIS data quality change parameter corresponding to the ship according to a plurality of comprehensive quality indexes in the analysis time period; obtaining a data quality change threshold; when the AIS data quality change parameter is greater than the data quality change threshold, determining that the data quality type of the ship is a second type.

7. The AIS data quality assessment method of claim 2, wherein, The AIS data quality evaluation method further comprises: determining historical AIS data of each grid area in the global heat map according to a plurality of historical trend curves; determining a historical average value corresponding to the grid comprehensive quality index score of the grid area according to the historical AIS data; when the grid comprehensive quality index score of the grid area is less than the historical average value, or when at least one of the dimension scores of the ship in the grid area is less than a quality score threshold, determining that the warning type is a first warning type.

8. The AIS data quality assessment method of claim 7, wherein, The AIS data quality evaluation method further comprises: determining a first warning parameter and a second warning parameter, the first warning parameter being less than the second warning parameter; when the comprehensive quality index score of the ship in the grid area is less than the first warning parameter or the grid comprehensive quality index score of the area is less than the second warning parameter, determining that the warning type is a second warning type.

9. An AIS data quality assessment apparatus, characterized by comprising: a data acquisition module for acquiring AIS data of a plurality of ships, the AIS data comprising ship static data, ship dynamic data and ship type; determining a sea area type corresponding to each of the ships, the sea area type comprising regional operation attributes and regional channel attributes; a frequency determining module configured to determine a data update interval threshold corresponding to each of the vessels according to the regional waterway attribute; a field module configured to determine a data integrity score according to the static data and dynamic data of the vessels; a time module configured to determine a device time corresponding to the vessels and determine a time synchronization score according to the device time and the world standard time; a signal determining module configured to determine a signal stability score according to the signal strength of the AIS data; a dynamic weight module configured to determine initial weights, the initial weights including a first initial weight corresponding to the update frequency score, a second initial weight corresponding to the integrity score, a third initial weight corresponding to the time synchronization score, and a fourth initial weight corresponding to the signal stability score; at least one emphasis index including a first emphasis index, a second emphasis index, a third emphasis index, and a fourth emphasis index according to the vessel type and the regional operation attribute corresponding to each of the vessels, and determine dimension weights corresponding to the update frequency score, the integrity score, the time synchronization score, and the signal stability score according to the emphasis index and the initial weights; a quality evaluation module configured to determine a comprehensive quality index of the vessels according to the dimension weights and dimension scores, the dimension scores including the update frequency score, the integrity score, the time synchronization score, and the signal stability score; the AIS data quality evaluation device is further configured to divide an electronic sea chart into a plurality of grid regions according to a 1x1 nautical mile grid based on the electronic sea chart, determine an average value of the comprehensive quality indexes of the plurality of vessels in the grid regions; determine a grid comprehensive quality index score according to the average value; color the grid regions according to the grid comprehensive quality index score to determine a global heat map.

10. An electronic device, comprising: The program or instructions stored on the readable storage medium are executed by the processor to implement the steps of the AIS data quality evaluation method according to any one of claims 1 to 8.

11. A readable storage medium, characterized by, The program or instructions stored on the readable storage medium are executed by the processor to implement the steps of the AIS data quality evaluation method according to any one of claims 1 to 8.

12. A chip, characterized by The chip includes a processor and a communication interface, the communication interface and the processor are coupled, the processor is used to run the program or instructions, and the steps of the AIS data quality evaluation method according to any one of claims 1 to 8 are implemented.

Images