Inland cargo classification and flow direction data calculation method, device, equipment and medium

Abstract

The application provides an inland river cargo classification flow direction data calculation method, device, equipment and medium, relates to the waterway transportation technical field, and comprises the following steps: acquiring basic voyage investigation data or stop investigation data corresponding to a plurality of sampling ships; for each sampling ship, converting the stop investigation data into corresponding voyage investigation data, and establishing a voyage data set; according to the water area interconnection matrix and the in-out port report data, correcting the start and end port area information of each sampling ship in the voyage data set, and according to the start and end port area information of each sampling ship, correcting the transportation distance of each sampling ship to obtain a second correction data set; inputting the second correction data set into a cargo flow direction calculation model to calculate the flow direction data of each type of cargo corresponding to the ship overall library. The technical scheme of the embodiment of the application improves the accuracy of the sampling data, can effectively eliminate the sample deviation, and significantly improves the calculation accuracy of the flow direction data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of waterway transportation, in particular to an inland river cargo sub-class flow direction data calculation method, device, equipment and medium. BACKGROUND

[0002] With the increasing importance of inland waterway transportation in regional economy, accurate acquisition and calculation of cargo flow direction data have become the key to optimizing transportation resource allocation and improving channel management efficiency.

[0003] At present, the acquisition and calculation of inland waterway sub-class flow direction data mainly adopts the following method: conducting investigation in local channels, that is, setting investigation points on specific navigation sections, conducting on-site inquiry on passing ships, collecting basic information such as cargo type, transportation volume and flow direction, and using sample data calculation method to calculate regional cargo flow direction based on investigation sample data by using direct summary method and proportion structure method. That is, the investigation sample data is simply added up, combined with the proportion of each cargo class in the sample, and combined with the total regional freight volume to calculate.

[0004] The local channel investigation method can only obtain freight information of specific navigation sections, and it is difficult to fully reflect the cargo circulation situation of the entire inland river system. At the same time, the existing method does not fully consider the sampling bias in sample investigation, resulting in insufficient accuracy of the calculation result. SUMMARY

[0005] Therefore, the purpose of the present application is to provide an inland river cargo sub-class flow direction data calculation method, device, equipment and medium, which improves the accuracy of sample data through multi-level correction, effectively eliminates sample bias, and significantly improves the calculation accuracy of flow direction data of all ships in the ship database for each type of cargo. In addition, the water area connection matrix and the port entry and exit report data are considered in the correction process, so that the data is more in line with the actual operation of inland transportation, and the practicality and effectiveness of the calculation result are enhanced.

[0006] In a first aspect, an inland river cargo sub-class flow direction data calculation method is provided, comprising:

[0007] Obtaining basic voyage investigation data or berthing investigation data corresponding to a plurality of sample ships;

[0008] For each sample ship, determining the voyage investigation data corresponding to each sample ship according to the plurality of berthing ports indicated by the berthing investigation data, and the loading data and unloading data corresponding to each berthing port;

[0009] Establishing a voyage data set according to the basic voyage investigation data or the voyage investigation data corresponding to each sample ship;

[0010] According to the preset water area connection matrix and the in-out port report data, the start and end port area information of each sampling ship in the voyage data set is corrected to obtain a first corrected data set;

[0011] According to the start and end port area information of each sampling ship in the first corrected data set, the transportation distance of each sampling ship in the first corrected data set is corrected to obtain a second corrected data set;

[0012] The second corrected data set is input into a cargo flow direction calculation model to calculate the flow direction data of each type of cargo corresponding to the ship overall library.

[0013] In the preferred embodiment of the present application, the above-mentioned obtaining of the basic voyage survey data or the stopover survey data corresponding to the plurality of sampling ships comprises:

[0014] According to the city, type and total tonnage of the ship, the plurality of ships included in the ship overall library are stratified to obtain the number of ships corresponding to each level;

[0015] According to the number of ships corresponding to each level, the number of sampling ships corresponding to each level is determined by an equal proportion allocation method;

[0016] According to the number of sampling ships, the basic voyage survey data or the stopover survey data corresponding to the sampling ships is obtained from the ships corresponding to each level.

[0017] In the preferred embodiment of the present application, the above-mentioned determining of the voyage survey data corresponding to each sampling ship according to the plurality of stopover ports indicated by the stopover survey data and the loading data and unloading data corresponding to each stopover port comprises:

[0018] For each sampling ship, according to the loading data and unloading data corresponding to each stopover port, the freight volume matrix and the container volume matrix corresponding to each stopover port are sequentially determined according to the stopover sequence of each stopover port;

[0019] For each sampling ship, the transportation distance corresponding to the non-zero elements in the freight volume matrix and the container volume matrix is determined according to the freight volume matrix and the container volume matrix;

[0020] For each sampling ship, the freight volume matrix, the container volume matrix and the transportation distance are taken as the voyage survey data corresponding to each sampling ship.

[0021] In the preferred embodiment of the present application, the above-mentioned correcting of the start and end port area information of each sampling ship in the voyage data set according to the preset water area connection matrix and the in-out port report data to obtain a first corrected data set comprises:

[0022] According to the preset water area connection matrix, the start and end port area information of each sampling ship in the voyage data set is compared to determine the matching failed voyage data;

[0023] The matching failed voyage data is matched with the in-out port report data to determine the in-port record and the out-port record corresponding to the matching failed voyage data;

[0024] According to the in-port record and the out-port record, the matching failed voyage data is updated to obtain updated voyage data;

[0025] The updated voyage data and the matching successful voyage data are taken as a first correction data set.

[0026] In a preferred embodiment of the present application, the above-mentioned correction of the transport distance of each sampling ship in the first correction data set according to the start and end port area information of each sampling ship in the first correction data set to obtain a second correction data set comprises:

[0027] According to the start and end port area information of each sampling ship in the first correction data set, a hierarchical start and end point combination corresponding to the start and end port area information is determined;

[0028] The transport distances corresponding to the sampling ships with the same hierarchical start and end point combination are determined as a transport distance group;

[0029] According to the first quartile and the third quartile corresponding to the transport distance group, an abnormal range of the transport distance group is determined;

[0030] Each transport distance in the transport distance group is compared with the abnormal range, and the transport distance outside the abnormal range is corrected to obtain a second correction data set.

[0031] In a preferred embodiment of the present application, the above-mentioned correction of the transport distance of each sampling ship in the first correction data set according to the start and end port area information of each sampling ship in the first correction data set to obtain a second correction data set comprises:

[0032] According to the start and end port area information of each sampling ship in the first correction data set, the start and end port area information is grouped according to the start port area and the end port area to obtain a first start and end point combination;

[0033] When the number of sampling ships with the same first start and end point combination is greater than or equal to a preset threshold, the first start and end point combination is taken as the hierarchical start and end point combination corresponding to the start and end port area information;

[0034] when the number of the sampling ships with the same first origin-destination combination is less than the preset threshold, grouping according to the origin cities and the destination cities of the origin port area and the destination port area in the origin-destination port area information to obtain a second origin-destination combination;

[0035] when the number of the sampling ships with the same second origin-destination combination is greater than or equal to the preset threshold, taking the second origin-destination combination as the hierarchical origin-destination combination corresponding to the origin-destination port area information;

[0036] when the number of the sampling ships with the same second origin-destination combination is less than the preset threshold, grouping according to the provinces of the origin port area and the destination port area in the origin-destination port area information to obtain a third origin-destination combination;

[0037] taking the third origin-destination combination as the hierarchical origin-destination combination corresponding to the origin-destination port area information.

[0038] In a second aspect, the embodiment of the present application further provides an inland cargo classification and flow direction data calculating device, comprising:

[0039] a data collection module, configured to acquire basic voyage investigation data or stopover investigation data corresponding to a plurality of sampling ships;

[0040] a data conversion module, configured to determine, for each sampling ship, voyage investigation data corresponding to the sampling ship according to a plurality of stopover ports indicated by the stopover investigation data and loading data and unloading data corresponding to each stopover port;

[0041] a data merging module, configured to establish a voyage data set according to the basic voyage investigation data or the voyage investigation data corresponding to each sampling ship;

[0042] a first correction module, configured to correct origin-destination port area information of each sampling ship in the voyage data set according to a preset water area connection matrix and an entry-exit port report data to obtain a first correction data set;

[0043] a second correction module, configured to correct a transportation distance of each sampling ship in the first correction data set according to the origin-destination port area information of the sampling ship in the first correction data set to obtain a second correction data set;

[0044] a data calculating module, configured to input the second correction data set into a cargo flow direction calculating model to calculate flow direction data of each type of cargo corresponding to a ship overall database.

[0045] In a third aspect, the embodiments of the present application further provide an electronic device, comprising a processor and a memory, the memory storing computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement the inland cargo sub-class flow direction data calculation method of the first aspect.

[0046] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, the computer readable storage medium storing computer executable instructions, and the computer executable instructions, when called and executed by a processor, cause the processor to implement the inland cargo sub-class flow direction data calculation method of the first aspect.

[0047] The embodiments of the present application bring the following beneficial effects:

[0048] The embodiments of the present application provide an inland cargo sub-class flow direction data calculation method, which considers the water area connection matrix and the in-out port report data to correct the information of the start and end port areas, and corrects the transportation distance by using the corrected information of the start and end port areas, realizes multi-level correction, improves the accuracy of the sampling data, makes the data more consistent with the actual operation of the inland transportation, can effectively eliminate the sample deviation, significantly improves the calculation accuracy of the flow data of all ships in the ship overall library for each type of cargo, and enhances the practicality and effectiveness of the calculation results.

[0049] Other features and advantages of the present application will be described in the following description, or can be known or determined without doubt from the description, or can be known by implementing the above-mentioned technologies of the present application.

[0050] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0052] Figure 1 A flow chart of an inland cargo sub-class flow direction data calculation method provided by the embodiments of the present application;

[0053] Figure 2 A flow chart of another inland cargo sub-class flow direction data calculation method provided by the embodiments of the present application;

[0054] Figure 3 A flowchart of another method for calculating the flow direction data of the inland river cargo by cargo type according to an embodiment of the present application is provided.

[0055] Figure 4 A structural schematic diagram of a device for calculating the flow direction data of the inland river cargo by cargo type according to an embodiment of the present application is provided.

[0056] Figure 5 A structural schematic diagram of an electronic device according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0057] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described below in detail with reference to the drawings. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0058] At present, the acquisition and calculation of the flow direction data of the inland river cargo by cargo type mainly adopts the following method. A local waterway is investigated, that is, a survey point is set at a specific navigation section, and the basic information such as the type, transportation volume and flow direction of the cargo is collected by on-site inquiry of the passing ships. The sample data calculation method is used to calculate the regional cargo flow direction based on the survey sample data by using the direct summary method and the proportion structure method. That is, the survey sample data is simply added up, combined with the proportion of each cargo type in the sample, and combined with the total regional freight volume to calculate the split.

[0059] The local waterway investigation method can only obtain the freight information of a specific navigation section, and it is difficult to fully reflect the cargo circulation situation of the entire inland river system. At the same time, the existing method does not fully consider the sampling bias in the sample survey, resulting in insufficient accuracy of the calculation result.

[0060] Based on this, the method, device, equipment and medium for calculating the flow direction data of the inland river cargo by cargo type according to the embodiments of the present application can improve the accuracy of the sampling data through multi-level correction, effectively eliminate the sample bias, and significantly improve the calculation accuracy of the flow direction data of all ships in the ship database for each type of cargo. In addition, the water area connection matrix and the port entry and exit report data are considered in the correction process, so that the data is more in line with the actual operation of the inland transportation, and the practicality and effectiveness of the calculation result are enhanced.

[0061] To facilitate the understanding of the embodiments, first, a method for calculating the flow direction data of the inland river cargo by cargo type according to the embodiments of the present application is described in detail.

[0062] Embodiment 1

[0063] The embodiment of the present application provides an inland cargo sub-class flow direction data calculation method, Figure 1 A flow chart of an inland cargo sub-class flow direction data calculation method is provided in the embodiment of the present application. Figure 1 As shown in the figure, the inland cargo sub-class flow direction data calculation method can include the following steps:

[0064] In step S101, basic voyage survey data or stop survey data corresponding to a plurality of sampling ships is acquired.

[0065] The sampling ship refers to a ship that needs to be sampled. In the embodiment of the present application, the ship total library includes all ships participating in cargo transportation in the inland water system. The sampling ship is a part of the ship total library, which is used to sample the data in the cargo transportation process to obtain the basic voyage survey data or the stop survey data of the sampling ship. The number of sampling ships is the minimum sampling number required by statistics, and can also be pre-specified according to actual conditions. The basic voyage survey data refers to the survey data that needs to be collected when the ship does not have intermediate loading and unloading during transportation, which at least includes the ship name, ship identification number, ship type, voyage number, start and end time, voyage starting point, loading port, unloading port, cargo type, transportation distance, cargo volume and container volume. The stop survey data refers to the survey data that needs to be collected when the ship has intermediate loading and unloading during transportation. When the sampling ship stops at a port and has loading and unloading, the data is collected once. Each time the collected data at least includes the ship name, ship identification number, ship type, voyage number, stop sequence number, stop time, stop port, distance from the last port, loading volume, unloading volume, container loading volume, container unloading volume, etc.

[0066] Specifically, for each sampling ship, the basic voyage survey data or the stop survey data is collected according to whether there is loading and unloading.

[0067] In step S102, for each sampling ship, the voyage survey data corresponding to each sampling ship is determined according to the plurality of stop ports indicated by the stop survey data, and the loading data and unloading data corresponding to each stop port.

[0068] For each sampling ship, for the sampling ship obtaining the berthing investigation data, since only the loading and unloading conditions are recorded each time the ship docks, the port of origin and destination of the goods cannot be directly obtained, and therefore the freight volume, container volume and actual transport distance between ports need to be calculated according to the loading data and unloading data, as the voyage investigation data corresponding to the sampling ship. The berthing port refers to the port where the sampling ship is located when there is loading and unloading during the voyage. The loading data refers to the weight of the goods loaded by the sampling ship, including the loading volume and the container loading volume. The loading volume refers to the weight of the goods loaded in tons, and the container loading volume refers to the number of containers loaded in containers. The unloading data refers to the weight of the goods unloaded by the sampling ship, including the unloading volume and the container unloading volume. The unloading volume refers to the weight of the goods unloaded in tons, and the container unloading volume refers to the number of containers unloaded in containers.

[0069] Specifically, for each sampling ship, according to the plurality of berthing ports indicated by the berthing investigation data, for each berthing port, the freight volume, container volume and actual transport distance between ports are calculated according to the loading data and the corresponding loading data and unloading data of each berthing port, as the voyage investigation data corresponding to the sampling ship. The freight volume refers to the weight of a certain type of goods transported by the sampling ship from the start of loading to the end of unloading in tons. The container volume refers to the number of containers transported by the sampling ship from the start of loading to the end of unloading. The actual transport distance refers to the distance traveled by the sampling ship from the start of loading to the end of unloading.

[0070] For example, assume that a river transport ship docks at port A, port B and port C in turn, and the specific loading and unloading conditions are as follows: at port A, the loading volume is 80 tons of steel, and the loading time point is the start time of the voyage, denoted as t1. At port B, the loading volume is 30 tons of food, and the loading time point is t2; the unloading volume is 50 tons of steel loaded from port A, and the unloading time point is t3. At port C, the unloading volume is the remaining steel (80 - 50 = 30 tons) and the 30 tons of food loaded at port B, and the unloading time points are t4 and t5, respectively. The process of assigning goods according to the loading and unloading time sequence is as follows:

[0071] Step 1: Initialization

[0072] After loading at port A, the remaining goods volume (i.e. the steel loaded from port A) is 80 tons, and the initial value of the transport volume matrix (which records the freight volume between ports) is 0.

[0073] Second step: handling the unloading of port B

[0074] Unloading: since the unloading of port B is 50 tons, according to the principle of preferential allocation of unloading of the first loading port, the steel loaded from port A is unloaded first. Therefore, the transportation matrix value from port A to port B is updated to 50 tons, and the remaining amount of steel loaded from port A is 80 - 50 = 30 tons.

[0075] Loading: after loading 30 tons (grain) in port B, the remaining amount increases by 30 tons (grain), and the transportation matrix in the loading part related to port B (such as from port B to the subsequent port) waits for subsequent unloading for allocation calculation.

[0076] Third step: handling the unloading of port C

[0077] Unloading: first handle the unloading of the remaining 30 tons of steel from port A, and update the transportation matrix value from port A to port C to 30 tons; then handle the unloading of the 30 tons of grain loaded in port B, and update the transportation matrix value from port B to port C to 30 tons.

[0078] In this way, the allocation of goods between different ports according to the order of loading and unloading is completed, and the freight between ports is determined, which can be further used to calculate the actual transportation distance. At port B, the 50 tons of steel unloaded from port B is transported from port A to port B, and the actual transportation distance is the distance from port A to port B. At port C, the 30 tons of steel unloaded from port C is transported from port A to port C, and the actual transportation distance is the distance from port A to port C. The 30 tons of grain unloaded from port C is transported from port B to port C, and the actual transportation distance is the distance from port B to port C.

[0079] The voyage survey data refers to the data obtained by converting the port survey data into basic voyage survey data, which is the same as the data included in the basic voyage survey data, wherein the actual transportation distance in the voyage survey data is equivalent to the transportation distance in the basic voyage survey data.

[0080] Step S103, according to the basic voyage survey data or the voyage survey data corresponding to each sampling ship, a voyage data set is established.

[0081] Specifically, for the sampling ship without intermediate loading and unloading during transportation, the basic voyage survey data collected by it is merged with the voyage survey data obtained by data conversion processing of the sampling ship with intermediate loading and unloading, so as to construct a voyage data set.

[0082] Step S104, according to the preset water area connection matrix and the port entry and exit report data, the start and end point port area information of each sampling ship in the voyage data set is corrected to obtain a first corrected data set.

[0083] The start and end point port area information refers to the start port and the end port of the sampling ship. The water area connection matrix is used to describe whether two ports can be connected through the inland water system. It can be understood that all provinces in China are included in the water area connection matrix. If the value in the water area connection matrix is 1, it means that the two provinces can be connected through the inland water system, that is, the ship can transport goods between the two provinces. If the value in the water area connection matrix is 0, it means that the two provinces cannot be connected through the inland water system, that is, the ship cannot transport goods between the two provinces. Exemplarily, the water area connection matrix is M i，j , the value of M i，j indicates whether the province i and the province j can be connected through the inland water system. The port entry and exit report data refers to the information registered by the ship when entering and exiting the port, which at least includes the ship identification number, the reporting port time, the stop port area and the reporting port category (entry / exit) and other information.

[0084] Specifically, for each sampling ship, according to the start and end point port area information of the sampling ship in the voyage data set, the value corresponding to the province where the start port is located and the province where the end port is located is queried from the water area connection matrix. If the value is 1, it means that the start and end point port area information is correct and does not need to be corrected. If the value is 0, it means that the start and end point port area information is incorrect and needs to be corrected. At this time, the reporting port record of the sampling ship is selected from the port entry and exit report data according to the ship identification number, and whether the province where the port is located in the reporting port record with the port category as exit is the same as the province where the start port is located and whether the province where the port is located in the reporting port record with the port category as entry is the same as the province where the end port is located are compared. If any of the two is different, the port in the reporting port record is replaced by the start and end ports, and the start and end point port area information of the sampling ship is corrected to obtain the first corrected data set.

[0085] Step S105, according to the start and end point port area information of each sampling ship in the first corrected data set, the transportation distance of each sampling ship in the first corrected data set is corrected to obtain a second corrected data set.

[0086] The transportation distance of the sampling ship is the distance between the starting port and the ending port. According to the starting and ending port information of each sampling ship in the first correction data set, the transportation distance of the ship is corrected by using a hierarchical progressive method. Specifically, in the same starting and ending port combination, when the number of records is greater than or equal to 5, the 25% quantile (Q1) and the 75% quantile (Q3) of the transportation distance of the group are calculated. The values outside the range of [Q1-1.5×(Q3-Q1), Q3+1.5×(Q3-Q1)] are marked as abnormal values, and the arithmetic mean of the non-abnormal values in the group is replaced. For combinations that do not meet the record quantity, upgrade to the city level of the starting and ending location, and use the range [Q1-2×(Q3-Q1), Q3+2×(Q3-Q1)] to perform secondary correction. For records that still cannot be processed, finally complete the correction in the provincial administrative district combination with a 3 times IQR threshold range of [Q1-3×(Q3-Q1), Q3+3×(Q3-Q1)].

[0087] Exemplarily, when 6 distance data (100, 105, 110, 115, 120, 200 km) from starting port A to ending port B are corrected at the port level, Q1=105 km, Q3=120 km, and IQR=15 km are calculated. It is determined that 200 km exceeds the normal range of 82.5-142.5 km, and it is replaced by the mean value of the reasonable values in the group, which is 110 km. For 3 records (including abnormal value 50 km) from starting port C to ending port D, the record quantity is insufficient, and it is upgraded to the city level combination for correction. C port belongs to Y city, and D port belongs to Z city. Combined with 1 data (distance 160 km) from C port to E port (E port belongs to Z city), a combination of starting Y city to ending Z city is formed, which has a total of 4 records (150, 155, 50, 160 km). Since the combination is still insufficient for 5, it needs to be upgraded to the provincial level for processing again. Y city belongs to P province, and Z city belongs to Q province. Combined with 1 data (distance 165 km) from C port to F port (F port belongs to Q province) and 1 data (distance 170 km) from C port to G port (G port belongs to Q province), a combination of starting P province and ending Q province is formed, which has a total of 6 data (150, 155, 50, 160, 165, 170 km). Q1=150 km, Q3=165 km, and IQR=15 km are calculated. Among them, 50 km exceeds the provincial range of 105-210 km, and it is finally corrected to the mean value of the non-abnormal values in the provincial group, which is 160 km.

[0088] In step S106, the second correction data set is input into the cargo flow direction estimation model to estimate the flow direction data of each type of cargo corresponding to the ship overall database.

[0089] The flow direction data of the freight includes total freight volume, total freight turnover, total container volume and total container turnover of different freight types and different directions. The second modified data set is input into the freight flow direction estimation model, and the freight flow direction estimation model calculates the freight turnover and the container turnover according to the freight volume, the container volume and the transportation distance in the second modified data set. The freight turnover = freight volume * transportation distance, and the container turnover = container volume * transportation distance. Then, the flow direction data of each type of freight is calculated according to the ratio of the sampling ships to all the ships in the ship library. That is, at least one sampling ship of the same type of freight transported from the same starting port to the same ending port is selected from each sampling ship, the sum of the freight volume of the selected sampling ships is multiplied by the ratio between the total number of ships in the ship library of the same level and the number of sampling ships, to obtain the total freight volume of the freight type and the direction. The total freight turnover, the total container volume and the total container turnover are calculated by the same principle.

[0090] The embodiment of the present application provides a kind of inland freight flow direction data estimation method for different freight types, consider the water area interconnection matrix and the information correction of starting and ending port area of report data, and utilize the starting and ending port area information of modified to correct transportation distance, realize multi-level correction, improve the accuracy of sampling data, make data more in line with the actual operation of inland transportation, can effectively eliminate sample deviation, significantly improve the estimation precision of the flow direction data of each type of freight of all the ships in the ship library, enhance the practicability and effectiveness of the estimation result.

[0091] Embodiment 2

[0092] The embodiment of the present application also provides another kind of inland freight flow direction data estimation method for different freight types;The method is realized based on the above-mentioned embodiment method;The method mainly describes the specific implementation mode of obtaining the basic voyage survey data or the berthing survey data corresponding to the plurality of sampling ships.

[0093] Figure 2 The flow chart of another kind of inland freight flow direction data estimation method for different freight types provided by the embodiment of the present application is shown in Figure 2 The inland freight flow direction data estimation method for different freight types can include the following steps:

[0094] Step S201, the plurality of ships included in the ship library are layered according to the city, type and total tonnage of the ship, to obtain the number of ships corresponding to each level.

[0095] The plurality of ships included in the ship overall database is grouped. First, the ships are grouped according to the cities to which the ships belong, to obtain the number of ships in each group in the first level grouping. Then, in each group of the first level, the ships are grouped according to the type, to obtain the number of ships in each group in the second level grouping. Then, in each group of the second level, the ships are grouped according to the total tonnage of the ships, to obtain the number of ships in each group in the third level grouping. The number of ships corresponding to each level refers to the number of ships in each group in the third level grouping.

[0096] Exemplarily, the hierarchical results are shown in Table 1, wherein the hierarchical grouping according to the cities to which the ships belong is not shown:

[0097] Table 1 Hierarchical results

[0098]

[0099] In step S202, according to the number of ships corresponding to each level, the number of sampling ships corresponding to each level is determined according to the equal proportion allocation method.

[0100] According to the number of ships corresponding to each level, a preset proportion is set, and the number of ships corresponding to each level is multiplied by the preset proportion to obtain the number of sampling ships corresponding to each level. That is, in each level of the three levels, the number of ships in each group is multiplied by the preset proportion to obtain the number of sampling ships in each group in each level.

[0101] Exemplarily, the number of sampling ships in the first group in the first level is the product of the number of ships in the first group in the first level and the preset proportion.

[0102] In step S203, according to the number of sampling ships, the basic voyage survey data or the stop survey data corresponding to the sampling ships is obtained from the ships corresponding to each level.

[0103] In each level of the three levels, for the ships in each group in each level, the number of sampling ships is determined according to the number of sampling ships, and the basic voyage survey data corresponding to the sampling ships is selected or the stop survey data corresponding to the sampling ships is selected according to whether the sampling ships have intermediate loading and unloading of goods.

[0104] In step S204, for each sampling ship, according to the plurality of stop ports indicated by the stop survey data and the loading data and unloading data corresponding to each stop port, the voyage survey data corresponding to each sampling ship is determined.

[0105] Specifically, the voyage survey data can be determined through steps A1-A3.

[0106] Step A1, for each sampling ship, according to the docking sequence of each of the docking ports, and according to the loading data and unloading data corresponding to each of the docking ports, determine the freight volume matrix and the container volume matrix corresponding to each of the docking ports in sequence.

[0107] Step A2, for each sampling ship, according to the freight volume matrix and the container volume matrix, determine the transportation distance corresponding to the non-zero elements in the freight volume matrix and the container volume matrix.

[0108] Step A3, for each sampling ship, take the freight volume matrix, the container volume matrix and the transportation distance as the voyage investigation data corresponding to each of the sampling ships.

[0109] Specifically, for each sampling ship, assuming that the port docks the ports in sequence are , wherein: is the starting port, the loading volume is , no unloading is 0. is the terminal port, only unloading, the unloading volume is all the remaining freight volume. The intermediate port may load and unload at the same time, the loading volume at the i-th port is , the unloading volume is . First check whether it is 0, if not, correct to 0; then check and whether they are equal, wherein , if not, correct, specifically, can increase or decrease to make equal to . Wherein refers to the sum of the loading volumes of n ports, refers to the sum of the unloading volumes of n ports.

[0110] Let the remaining volume be , and the remaining volume of the remaining ports is initialized to 0, i.e. . The transportation volume matrix represents the freight volume from port to , and is initialized to 0.

[0111] For each port , perform the following operations:

[0112] a) handle the unloading of the current port: (1) calculate the unloading volume of the current port ​If k = n, all the remaining cargo needs to be unloaded, i.e. , otherwise, the preset unloading amount is directly used ; (2) the unloading amount is allocated according to the loading sequence, starting from the port where the earliest loading is performed , , , and the process is repeated until or all are allocated.

[0113] b) handle the loading situation of the current port: if , update the remaining amount of .

[0114] Traverse the matrix , output all non-zero , and calculate the transportation distance between the corresponding , , which is the cumulative distance of all intermediate adjacent ports from to . Calculate the container transportation matrix according to the above allocation principle to obtain voyage survey data, including basic information of each voyage ship, voyage start and end port area, cargo volume, container volume, transportation distance, etc. Among them, the cargo volume refers to each value in the cargo volume matrix, and the container volume refers to each value in the container volume matrix.

[0115] Exemplarily, assume that a ship successively stops at ports P_0, P_1, P_2, P_3, P_0 has a loading amount x_0 = 100 tons, P_1 has a loading amount x_1 = 50 tons, and an unloading amount y_1 = 30 tons; P_2 has a loading amount x_2 = 20 tons, and an unloading amount y_2 = 40 tons; P_3 has an unloading amount of all remaining cargo.

[0116] First, check y_0 (initially 0, which meets the requirements), then calculate ∑x_i = 100 + 50 + 20 = 170 tons, and calculate the total unloading amount (without considering the final unloading amount of P_3) as y_1 + y_2 = 30 + 40 = 70 tons, which will be adjusted according to the unloading situation of P_3 to ensure data accuracy.

[0117] Initialize the remaining amount r_0 = 100 tons, r_1 = 0 tons, r_2 = 0 tons, and the transportation matrix T_(i,j) is initialized to 0.

[0118] ​

[0119] For port P_1:

[0120] Discharge amount y_1 = 30 tons, allocate discharge amount from the earliest loading port P_0, t_(0,1) = min(r_0, y_1) = min(100, 30) = 30 tons, r_0 = 100 - 30 = 70 tons, y_1 = 30 - 30 = 0 tons.

[0121] After loading, r_1 = x_1 = 50 tons.

[0122] For port P_2:

[0123] Discharge amount y_2 = 40 tons, allocate discharge amount from the earliest loading port (at this time r_0 = 70 tons, r_1 = 50 tons), t_(0,2) = min(r_0, y_2) = min(70, 40) = 40 tons, r_0 = 70 - 40 = 30 tons, y_2 = 40 - 40 = 0 tons.

[0124] After loading, r_2 = x_2 = 20 tons.

[0125] For port P_3:

[0126] Discharge amount y_3 = r_0 + r_1 + r_2 = 30 + 50 + 20 = 100 tons.

[0127] Traverse the transportation matrix to get non-zero t_(0,1) = 30 tons, t_(0,2) = 40 tons, etc., calculate the transportation distance d_(0,1), d_(0,2) between ports (assuming the distance between adjacent ports is known, and the transportation distance between ports is calculated).

[0128] According to the above allocation principle, calculate the container volume (assuming the number of containers corresponding to each batch of goods is known), and finally generate a shipping cargo volume manifest containing basic information of the ship (such as ship name, identification number, etc.), voyage start and end port area (P_0 to P_3), cargo volume (cargo volume between ports, such as P_0 to P_1 is 30 tons, etc.), container volume and voyage mileage (sum of distances calculated for each segment) and other indicators. The collection of voyage cargo volume manifests of each sampling ship is the voyage survey data.

[0129] Step S205, according to the basic voyage survey data or the voyage survey data corresponding to each of the sampling ships, a voyage data set is established.

[0130] Step S206, according to the preset water area connection matrix and the port report data, the start and end port area information of each sampling ship in the voyage data set is corrected to obtain a first correction data set.

[0131] Step S207, according to the start and end port area information of each sampling ship in the first correction data set, the transportation distance of each sampling ship in the first correction data set is corrected to obtain a second correction data set.

[0132] Step S208, inputting the second correction data set into the cargo flow direction calculation model to calculate the flow direction data of each type of cargo corresponding to the ship overall warehouse.

[0133] Specifically, the voyage survey data can be determined through steps B1-B6.

[0134] Step B1, according to the cargo volume, the container volume and the transportation distance of each sampling ship in the second correction data set, the cargo turnover and the container turnover of each sampling ship are determined.

[0135] Step B2, according to the corresponding level of each sampling ship, the calculation factor corresponding to each sampling ship is determined.

[0136] Step B3, for each type of cargo, the product of the calculation factor corresponding to each sampling ship with the same start and end port area information and the cargo volume is added to obtain the total cargo volume.

[0137] Step B4, for each type of cargo, the product of the calculation factor corresponding to each sampling ship with the same start and end port area information and the container volume is added to obtain the total container volume.

[0138] Step B5, for each type of cargo, the product of the calculation factor corresponding to each sampling ship with the same start and end port area information and the cargo turnover is added to obtain the total cargo turnover.

[0139] Step B6, for each type of cargo, the product of the calculation factor corresponding to each sampling ship with the same start and end port area information and the container turnover is added to obtain the total container turnover.

[0140] Specifically, according to the cargo volume, the container volume and the transportation distance of each sampling ship in the second correction data set, the cargo turnover and the container turnover of each sampling ship are determined.

[0141] The cargo turnover = cargo volume * transportation distance, and the container turnover = container volume * transportation distance. The level corresponding to the sampling ship refers to the group to which the sampling ship belongs in the third level. For each sampling ship, according to the level corresponding to the sampling ship, the calculation factor corresponding to each sampling ship is determined, and the calculation factor is determined as follows:

[0142]

[0143] the number of ships in the ship population for level b, the number of sampled ships for level b, the estimation factor.

[0144] For each sampled ship, the voyage survey data records the origin port , the destination port , the cargo type , the cargo volume , the cargo turnover , the container volume and the container turnover .

[0145] For each type of cargo, the total cargo volume is obtained by adding the product of the estimation factor and the cargo volume for each sampled ship having the same origin and destination port information.

[0146] That is, for each type of cargo, the total cargo volume is obtained by adding the product of the estimation factor and the cargo volume for each sampled ship having the same origin and destination port information.

[0147] Exemplarily, the total cargo volume can be calculated by the following formula:

[0148]

[0149] wherein, denotes the total cargo volume for the origin port i, the destination port j, the cargo type o; denotes the estimation factor for the sampled ship k; denotes the cargo volume for the sampled ship k, and K denotes the ship population.

[0150] For each type of cargo, the total container volume is obtained by adding the product of the estimation factor and the container volume for each sampled ship having the same origin and destination port information. For each type of cargo, the total cargo turnover is obtained by adding the product of the estimation factor and the cargo turnover for each sampled ship having the same origin and destination port information. For each type of cargo, the total container turnover is obtained by adding the product of the estimation factor and the container turnover for each sampled ship having the same origin and destination port information.

[0151] That is, the calculation principle of the total container volume, the total cargo turnover and the total container turnover is the same as the calculation principle of the total freight volume, and details are not repeated.

[0152] The inland cargo flow direction data calculation method provided by the embodiment of the present application realizes stratified sampling by stratifying the ships and determining the number of sampling ships according to the number of ships corresponding to each level, and on this basis, realizes flow direction data calculation based on stratified sampling weight by setting a weight for each level, which can effectively eliminate sample bias and significantly improve the calculation accuracy of flow direction data, accurately calculate the total freight volume, cargo turnover, container volume and container turnover of different flow directions of each cargo class, and has wide application value and popularization potential.

[0153] Embodiment 3

[0154] The embodiment of the present application also provides another inland cargo flow direction data calculation method for different cargo classes; the method is realized on the basis of the above-mentioned embodiment method; the method mainly describes the specific implementation mode of the first correction data set and the second correction data set.

[0155] Figure 3 The flow chart of another inland cargo flow direction data calculation method for different cargo classes provided by the embodiment of the present application is shown in Figure 3 The inland cargo flow direction data calculation method for different cargo classes can include the following steps:

[0156] Step S301, obtaining basic voyage survey data or stop survey data corresponding to a plurality of sampling ships.

[0157] Step S302, for each sampling ship, determining the voyage survey data corresponding to each sampling ship according to a plurality of stop ports indicated by the stop survey data and the loading data and unloading data corresponding to each stop port.

[0158] Step S303, establishing a voyage data set according to the basic voyage survey data or the voyage survey data corresponding to each sampling ship.

[0159] Step S304, comparing the start and end port area information of each sampling ship in the voyage data set with the pre-set water area connection matrix to determine the voyage data that fails to match.

[0160] The voyage data refers to the basic voyage survey data or the voyage survey data corresponding to a sampling ship in the voyage data set.

[0161] Specifically, for each sampling ship, according to the start and end port area information in the voyage data, the value corresponding to the province where the start port is located and the province where the end port is located in the water area connection matrix is queried. If the value is 1, it indicates that the start and end port area information is correct and does not need to be corrected, and the voyage data is determined as matching successful voyage data. If the value is 0, it indicates that the start and end port area information is incorrect and needs to be corrected, and the voyage data is determined as matching failed voyage data.

[0162] Step S305, matching the matching failed voyage data with the entry and exit port report data to determine the entry record and exit record corresponding to the matching failed voyage data.

[0163] Specifically, the ship identification number is obtained from the matching failed voyage data, and the entry record and exit record of the ship identification number are screened out from the entry and exit port report data according to the ship identification number. The entry record and exit record within 3 days before and after the voyage start and end time of the ship identification number can be screened out. The voyage start and end time can be queried from the voyage data.

[0164] Step S306, updating the matching failed voyage data according to the entry record and the exit record to obtain updated voyage data.

[0165] If the province where the port is located in the entry record is the same as the province where the end port is located in the voyage data, and the province where the port is located in the exit record is different from the province where the start port is located in the voyage data, the port in the exit record is replaced by the start port to obtain the updated voyage data. If the province where the port is located in the entry record is different from the province where the end port is located in the voyage data, and the province where the port is located in the exit record is the same as the province where the start port is located in the voyage data, the port in the entry record is replaced by the end port to obtain the updated voyage data.

[0166] If the province where the port is located in the entry record is different from the province where the end port is located in the voyage data, and the province where the port is located in the exit record is different from the province where the start port is located in the voyage data, the screening range of the entry record and the exit record can be expanded, and step S305 is returned to be executed.

[0167] Step S307, taking the updated voyage data and the matching successful voyage data as the first corrected data set.

[0168] Further, in the matching failed voyage data, if it cannot be corrected through steps S305 to S306, the following methods can also be sequentially executed for correction:

[0169] 1) Single-end matching data correction. For each sampling ship, according to the start and end time in the navigation data, the start port, end port and start and end time in the voyage data are selected from the port entry and exit report data. The port of departure record with the same start time as the start time and the port of arrival record with the same end time as the end time are selected from the port entry and exit report data. If the port in the port of departure record is the same as the start port, and the port in the port of arrival record is different from the end port, the port in the port of arrival record can be replaced by the end port. At this time, the value corresponding to the province where the start port is located and the province where the port in the port of arrival record is located is queried from the water area connection matrix. If the value is 1, it means that it can be replaced, if the value is 0, it means that it cannot be replaced, and the correction method needs to be changed. Conversely, if the port in the port of departure record is different from the start port, and the port in the port of arrival record is the same as the end port, the port in the port of departure record can be replaced by the start port. At this time, the value corresponding to the province where the end port is located and the province where the port in the port of departure record is located is queried from the water area connection matrix. If the value is 1, it means that it can be replaced, if the value is 0, it means that it cannot be replaced, and the correction method needs to be changed.

[0170] 2) Unmatched data classification processing. On the basis of method 1), if the port in the port of departure record is different from the start port, and the port in the port of arrival record is different from the end port, according to the port entry and exit report data, for each sampling ship, the classification summary of the port of call is carried out. If all the ports of call are in the same province, the start port and the end port of the sampling ship are recorded as the province. Among them, the port of call can be all the ports in the port of arrival record and the port of departure record selected from the port entry and exit report data according to the ship identification number.

[0171] 3) Easy-to-error port data set construction and application. Based on the above corrected records, the records in which the corresponding relationship between the error port and the correct port appears more than 3 times are established as the easy-to-error port data set. The remaining unmatched voyage data and the easy-to-error port data set are matched. That is, the start port and the end port in the unmatched voyage data are compared with the error port in the easy-to-error port data set. If they are the same, it means that the matching is successful, and the correct port corresponding to the error port is replaced by the matched port in the voyage data.

[0172] 4) Other error processing rules. For other error records, the following rules are used for correction:

[0173] a) If one of the start port and the end port is in the same province as the port of the sampling ship, it is determined that the port is the correct port; wherein the port of the sampling ship can be queried from the voyage data.

[0174] b) modifying another port. If the correct port is the origin port, in the matching failed voyage data, according to the transportation distance, the origin port is the same, and the transportation distance difference is within 20% from the historical voyage data set, the historical voyage data is queried, and the port with the highest frequency of occurrence of the destination port in the historical voyage data is replaced with the destination port in the matching failed voyage data. If the correct port is the destination port, the principle is the same and will not be repeated.

[0175] c) deleting the redundant records that cannot be matched.

[0176] Step S308, according to the origin and destination port area information of each sampling ship in the first modified data set, determine the hierarchical origin and destination combination corresponding to the origin and destination port area information.

[0177] In the first modified data set, the voyage records of a plurality of sampling ships are included, and each sampling ship's voyage record contains the origin port area, the destination port area and the transportation distance. In the embodiment of the present application, the transportation distance is corrected by using a hierarchical progressive mechanism. Among them, the hierarchical origin and destination combination refers to the combination of the origin port and the destination port.

[0178] Specifically, the origin and destination port area information of each sampling ship in the first modified data set is grouped according to different levels, and the origin port and the destination port in each group of sampling ships belong to the same hierarchical origin and destination combination. Among them, the level includes the port area, the city and the province.

[0179] Specifically, according to the origin and destination port area information of each sampling ship in the first modified data set, the hierarchical origin and destination combination corresponding to the origin and destination port area information is determined, including: according to the origin and destination port area information of each sampling ship in the first modified data set, grouping according to the origin port area and the destination port area in the origin and destination port area information to obtain the first origin and destination combination; when the number of sampling ships with the same first origin and destination combination is greater than or equal to a preset threshold, the first origin and destination combination is taken as the hierarchical origin and destination combination corresponding to the origin and destination port area information; when the number of sampling ships with the same second origin and destination combination is less than the preset threshold, grouping according to the city to which the origin port area and the destination port area belong to obtain the second origin and destination combination; when the number of sampling ships with the same second origin and destination combination is greater than or equal to a preset threshold, the second origin and destination combination is taken as the hierarchical origin and destination combination corresponding to the origin and destination port area information; when the number of sampling ships with the same second origin and destination combination is less than the preset threshold, grouping according to the province to which the origin port area and the destination port area belong to obtain the third origin and destination combination; the third origin and destination combination is taken as the hierarchical origin and destination combination corresponding to the origin and destination port area information.

[0180] It can be understood that the starting port area and the ending port area of each sampling ship are read from the first correction data set. The sampling ships with the same starting port area and the ending port area are grouped, that is, grouped according to the port area to which the starting port area and the ending port area in the starting and ending port area information belong, to obtain a plurality of first starting and ending port combinations. For each first starting and ending port combination, the number of sampling ships in the group is counted, and when the number of sampling ships in the group is greater than or equal to a preset threshold, the first starting and ending port combination is taken as the hierarchical starting and ending port combination corresponding to the starting and ending port area information, and step S309 is executed. For all sampling ships that do not satisfy the foregoing condition, that is, when the number of sampling ships in the group is less than the preset threshold, the starting and ending port area information is grouped according to the city to which the starting port area and the ending port area belong, to obtain a second starting and ending port combination. For each second starting and ending port combination, the number of sampling ships in the group is counted, and when the number of sampling ships in the group is greater than or equal to a preset threshold, the second starting and ending port combination is taken as the hierarchical starting and ending port combination corresponding to the starting and ending port area information, and step S309 is executed. For all sampling ships that do not satisfy the foregoing condition, that is, when the number of sampling ships in the group is less than the preset threshold, the starting and ending port area information is grouped according to the province to which the starting port area and the ending port area belong, to obtain a third starting and ending port combination. For each third starting and ending port combination, the number of sampling ships in the group is counted, and when the number of sampling ships in the group is greater than or equal to a preset threshold, the third starting and ending port combination is taken as the hierarchical starting and ending port combination corresponding to the starting and ending port area information, and step S309 is executed. The preset threshold can be set according to actual conditions. For example, the preset threshold can be set to 5.

[0181] In step S309, the transportation distances of the sampling ships corresponding to the same hierarchical starting and ending port combination are determined as a transportation distance group.

[0182] For the sampling ships belonging to the same hierarchical starting and ending port combination, the transportation distances of the sampling ships are queried from the first correction data set, and the transportation distances of the sampling ships are taken as the transportation distance group.

[0183] In step S310, the abnormal range of the transportation distance group is determined according to the first quartile and the third quartile of the transportation distance group.

[0184] For each transportation distance group, the transportation distances are arranged in ascending order, and the first quartile (that is, the 25% quantile, that is, Q1) and the third quartile (that is, the 75% quantile, that is, Q3) of the transportation distance group are determined. Specifically, the positions of the 25% quantile and the 75% quantile can be determined by the following formula:

[0185] i Q1 = (n+1) / 4

[0186] i Q3 = 3(n+1) / 4

[0187] wherein i Q1 denotes the position of the 25th percentile, i Q3 denotes the position of the 75th percentile, n denotes the number of transportation distances in the transportation distance group, Q1 denotes the 25th percentile, and Q3 denotes the 75th percentile.

[0188] Q1 is the transportation distance located at the i Q1 th position after the transportation distances are arranged in ascending order. Q3 is the transportation distance located at the i Q3 th position after the transportation distances are arranged in ascending order.

[0189] Further, the abnormal range of the transportation distance group is determined according to the 25th percentile and the 75th percentile of the transportation distance group, including: determining a interquartile range IQR according to the 25th percentile and the 75th percentile; and determining the abnormal range of the transportation distance group according to the 25th percentile, the 75th percentile and the interquartile range.

[0190] Specifically, the interquartile range IQR can be determined by the following formula: IQR = Q3 - Q1. At this time, the abnormal range can be determined as [Q1 - k i × IQR, Q3 + k i × IQR], wherein k i is a first constant, and i is a level. It can be understood that i is 2, indicating that the level is a port area, i is 3, indicating that the level is a city, and i is 1, indicating that the level is a province. k1, k2 and k3 can be set according to actual conditions, but must satisfy k1 > k2 > k3. For example, k1, k2 and k3 are respectively set as 1.5, 2 and 3.

[0191] In step S311, each transportation distance in the transportation distance group is compared with the abnormal range, and the transportation distance located outside the abnormal range is corrected to obtain a second corrected data set.

[0192] For each transportation distance group, each transportation distance in the transportation distance group is compared with the abnormal range, and the transportation distance located outside the abnormal range is corrected to obtain a second corrected data set. In the correction, the average value of at least one transportation distance located within the abnormal range in the transportation distance group can be used to replace and correct the transportation distance located outside the abnormal range.

[0193] In an implementation manner, the process of obtaining the second corrected data set is as follows:

[0194] (a) Grouping the voyage records of the same origin port area and destination port area, when the number of records in the group is greater than or equal to a preset threshold: calculating the first quartile Q1 and the third quartile Q3 of the transportation distance of the group; determining the first outlier range [Q1-k1*IQR, Q3+k1*IQR] based on IQR=Q3-Q1, wherein k1 is a first constant; replacing the outliers beyond the range with the arithmetic mean of the non-outliers in the group;

[0195] (b) Re-grouping the records that do not meet the record number threshold of step (a) according to the city where the origin port area is located and the city where the destination port area is located, when the number of records in the group is greater than or equal to a preset threshold: calculating Q1 and Q3 of the transportation distance of the city group; determining the second outlier range [Q1-k2*IQR, Q3+k2*IQR] based on IQR, wherein k2>k1; replacing the outliers beyond the range with the arithmetic mean of the non-outliers in the group;

[0196] (c) Re-grouping the records that do not meet the record number threshold of step (b) according to the province where the origin port area is located and the province where the destination port area is located: calculating Q1 and Q3 of the transportation distance of the province group; determining the third outlier range [Q1-k3*IQR, Q3+k3*IQR] based on IQR, wherein k3>k2; replacing the outliers beyond the range with the arithmetic mean of the non-outliers in the group; outputting the corrected second corrected data set.

[0197] Step S312, inputting the second corrected data set into the cargo flow estimation model to estimate the flow direction data of each type of cargo corresponding to the ship overall warehouse.

[0198] The inland cargo sub-class flow direction data estimation method provided by the embodiments of the present application realizes multi-level detection and correction through multiple correction methods for matching failed voyage data, and through the establishment of a voyage transportation distance detection and correction system and the accurate identification and processing of abnormal data through statistical methods, the accuracy of the data is significantly improved.

[0199] Embodiment 4

[0200] Corresponding to the above method embodiments, the embodiments of the present application provide an inland cargo sub-class flow direction data estimation device, Figure 4 The structure diagram of an inland cargo sub-class flow direction data estimation device provided by the embodiments of the present application is shown in Figure 4 As shown in the figure, the inland cargo sub-class flow direction data estimation device can include:

[0201] The data acquisition module 401 is configured to obtain basic voyage survey data or stop survey data corresponding to a plurality of sampling ships.

[0202] The data conversion module 402 is configured to determine voyage investigation data corresponding to each sampling ship according to a plurality of port of call indicated by the port of call investigation data and the loading data and the unloading data corresponding to each port of call.

[0203] The data merging module 403 is configured to establish a voyage data set according to the basic voyage investigation data or the voyage investigation data corresponding to each sampling ship.

[0204] The first correction module 404 is configured to correct the start and end port area information of each sampling ship in the voyage data set according to a preset water area connection matrix and the in-out port report data, and obtain a first correction data set.

[0205] The second correction module 405 is configured to correct the transportation distance of each sampling ship in the first correction data set according to the start and end port area information of each sampling ship in the first correction data set, and obtain a second correction data set.

[0206] The data calculation module 406 is configured to input the second correction data set into a cargo flow direction calculation model to calculate the flow direction data of each type of cargo corresponding to the ship general pool.

[0207] The embodiment of the present application provides an inland river cargo sub-class flow direction data calculation method, considers the correction of the start and end port area information according to the water area connection matrix and the in-out port report data, and corrects the transportation distance according to the corrected start and end port area information, realizes multi-level correction, improves the accuracy of the sampling data, makes the data more consistent with the actual operation of the inland river transportation, can effectively eliminate the sample deviation, significantly improves the calculation precision of the flow direction data of each type of cargo corresponding to all ships in the ship general pool, and enhances the practicability and effectiveness of the calculation result.

[0208] In some embodiments, the data collection module 401 is further configured to:

[0209] The plurality of ships included in the ship general pool are stratified according to the city, type and total tonnage of the ship, and the number of ships corresponding to each level is obtained.

[0210] According to the number of ships corresponding to each level, the number of sampling ships corresponding to each level is determined according to the equal proportion allocation method.

[0211] According to the number of sampling ships, the basic voyage investigation data or the port of call investigation data corresponding to the sampling ships is obtained from the ships corresponding to each level.

[0212] In some embodiments, the data conversion module 402 is further configured to:

[0213] For each sampling ship, according to the docking sequence of each of the docking ports, and according to the loading data and unloading data corresponding to each of the docking ports, a freight volume matrix and a container volume matrix corresponding to each of the docking ports are determined in sequence;

[0214] For each sampling ship, according to the freight volume matrix and the container volume matrix, a transportation distance corresponding to a non-zero element in the freight volume matrix and the container volume matrix is determined;

[0215] For each sampling ship, the freight volume matrix, the container volume matrix, and the transportation distance are taken as voyage investigation data corresponding to each of the sampling ships.

[0216] In some embodiments, the first correction module 404 is further configured to:

[0217] According to the preset water area connection matrix, the start and end port area information of each sampling ship in the voyage data set is compared to determine voyage data that fails to match;

[0218] The voyage data that fails to match is matched with the in-out port report data to determine in-port records and out-port records corresponding to the voyage data that fails to match;

[0219] According to the in-port records and the out-port records, the voyage data that fails to match is updated to obtain updated voyage data;

[0220] The updated voyage data and the voyage data that succeeds to match are taken as a first correction data set.

[0221] In some embodiments, the second correction module 405 is further configured to:

[0222] According to the start and end port area information of each sampling ship in the first correction data set, a hierarchical start and end port combination corresponding to the start and end port area information is determined;

[0223] Transportation distances corresponding to sampling ships having the same hierarchical start and end port combination are determined as a transportation distance group;

[0224] According to a first quartile and a third quartile corresponding to the transportation distance group, an abnormal range of the transportation distance group is determined;

[0225] Each of the transportation distances in the transportation distance group is compared with the abnormal range, and a transportation distance located outside the abnormal range is corrected to obtain a second correction data set.

[0226] In some embodiments, the second correction module 405 is further configured to:

[0227] grouping the sampling ships in the first correction data set according to the start and end port area information in the start and end port area information, to obtain first start and end port area combinations;

[0228] when the number of sampling ships with the same first start and end port area combination is greater than or equal to a preset threshold, taking the first start and end port area combination as the hierarchical start and end port area combination corresponding to the start and end port area information;

[0229] when the number of sampling ships with the same first start and end port area combination is less than the preset threshold, grouping the sampling ships according to the city to which the start and end port area in the start and end port area information belongs, to obtain second start and end port area combinations;

[0230] when the number of sampling ships with the same second start and end port area combination is greater than or equal to a preset threshold, taking the second start and end port area combination as the hierarchical start and end port area combination corresponding to the start and end port area information;

[0231] when the number of sampling ships with the same second start and end port area combination is less than the preset threshold, grouping the sampling ships according to the province to which the start and end port area in the start and end port area information belongs, to obtain third start and end port area combinations;

[0232] taking the third start and end port area combination as the hierarchical start and end port area combination corresponding to the start and end port area information.

[0233] In some embodiments, the data estimation module 406 is further configured to:

[0234] determining the cargo turnover and the container turnover of each of the sampling ships according to the cargo volume, the container volume and the transportation distance of each of the sampling ships in the second correction data set;

[0235] determining the estimation factor corresponding to each of the sampling ships according to the hierarchy corresponding to each of the sampling ships;

[0236] for each type of cargo, adding the product of the estimation factor corresponding to each of the sampling ships with the same start and end port area information and the cargo volume, to obtain the total cargo volume;

[0237] for each type of cargo, adding the product of the estimation factor corresponding to each of the sampling ships with the same start and end port area information and the container volume, to obtain the total container volume;

[0238] for each type of cargo, adding the product of the estimation factor corresponding to each of the sampling ships with the same start and end port area information and the cargo turnover, to obtain the total cargo turnover;

[0239] for each type of cargo, adding the product of the estimation factor corresponding to each of the sampling ships with the same start and end port area information and the container turnover, to obtain the total container turnover.

[0240] The device provided by the embodiments of the present application has the same implementation principle and generated technical effects as the foregoing method embodiments, and for brevity of description, the part not mentioned in the device embodiments can be referred to the corresponding content in the foregoing method embodiments.

[0241] Embodiment 5

[0242] The embodiments of the present application also provide an electronic device for running the above-mentioned inland cargo classified flow direction data calculation method; refer to Figure 5 The electronic device shown in the structural schematic diagram of the electronic device, the electronic device includes a memory 500 and a processor 501, wherein the memory 500 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 501 to realize the above-mentioned inland cargo classified flow direction data calculation method.

[0243] Further, Figure 5 The electronic device shown also includes a bus 502 and a communication interface 503, and the processor 501, the communication interface 503 and the memory 500 are connected through the bus 502.

[0244] Among them, the memory 500 can contain a high-speed random access memory (RAM, Random Access Memory), and can also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Through at least one communication interface 503 (which can be wired or wireless), the communication connection between the system network element and at least one other network element can be realized, and the Internet, a wide area network, a local network, a metropolitan area network, etc. can be used. The bus 502 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of expression, Figure 5 In the figure, only one bidirectional arrow is used to represent, but it does not mean that there is only one bus or one type of bus.

[0245] The processor 501 can be an integrated circuit chip having a signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 501 or the instruction in the form of software. The processor 501 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Each method, step and logic block diagram disclosed in the embodiment of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiment of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the storage 500 is read by the processor 501, and the hardware thereof is combined to complete the steps of the method of the above embodiment.

[0246] The embodiment of the present application further provides a computer readable storage medium, the computer readable storage medium stores computer executable instructions, when the computer executable instructions are called and executed by a processor, the computer executable instructions cause the processor to implement the above-mentioned inland cargo classification flow data calculation method, and specific implementation can be referred to the method embodiment, and will not be repeated here.

[0247] The computer program product for calculating the inland cargo classification flow data calculation method provided by the embodiment of the present application comprises a computer readable storage medium storing non-volatile program codes executable by a processor, and the instructions included in the program codes can be used to execute the method described in the foregoing method embodiment, and specific implementation can be referred to the method embodiment, and will not be repeated here.

[0248] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0249] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. The described device embodiments are merely schematic, and for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electric, mechanical or other forms.

[0250] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to the actual needs to achieve the purposes of the embodiments of the present application.

[0251] In addition, each function unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit.

[0252] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that make essential contributions to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0253] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the present application, and the protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still make modifications or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features therein, within the technical range disclosed by the present application. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for estimating the flow direction of inland waterway cargo by category, characterized in that, include: Obtain basic voyage survey data or docking survey data corresponding to multiple sampling vessels; For each sampled vessel, based on the multiple ports of call indicated by the berthing survey data, and the loading and unloading data corresponding to each port of call, the voyage survey data corresponding to each sampled vessel is determined; A voyage dataset is established based on the basic voyage survey data or the voyage survey data corresponding to each of the sampled vessels; Based on the preset waterway connectivity matrix and port entry / exit report data, the origin and destination port information of each sampled vessel in the voyage dataset is corrected to obtain the first corrected dataset. Based on the origin and destination port information of each sampled vessel in the first corrected dataset, the transportation distance of each sampled vessel in the first corrected dataset is corrected to obtain the second corrected dataset. Based on the cargo volume, container volume, and transport distance of each sampled vessel in the second corrected dataset, determine the cargo turnover and container turnover of each sampled vessel. Based on the level corresponding to each of the sampled vessels, the calculation factor corresponding to each sampled vessel is determined; For each type of cargo, the product of the estimation factor corresponding to each sampled vessel with the same origin and destination port information and the cargo volume is added together to obtain the total cargo volume; For each type of cargo, the product of the estimation factor corresponding to each sampled vessel with the same origin and destination port information and the container volume is added to obtain the total container volume; For each type of cargo, the total cargo turnover is obtained by adding the product of the estimation factor corresponding to each sampled vessel with the same origin and destination port information and the cargo turnover. For each type of cargo, the product of the estimation factor corresponding to each sampled vessel with the same origin and destination port information and the container turnover is added to obtain the total container turnover.

2. The method according to claim 1, characterized in that, The acquisition of basic voyage survey data or docking survey data corresponding to multiple sampling vessels includes: Based on the city, type, and gross tonnage of the vessels, the vessels in the overall vessel database are stratified to obtain the number of vessels corresponding to each stratum; Based on the number of ships corresponding to each level, the number of sampling ships corresponding to each level is determined according to the proportional allocation method. Based on the number of vessels sampled, basic voyage survey data or docking survey data corresponding to the sampled vessels are obtained from the vessels corresponding to each level.

3. The method according to claim 2, characterized in that, For each sampled vessel, based on the multiple ports of call indicated by the berthing survey data, and the loading and unloading data corresponding to each port of call, the voyage survey data corresponding to each sampled vessel is determined, including: For each sampled vessel, according to the berthing order of each port, and based on the loading and unloading data corresponding to each port, the cargo volume matrix and container volume matrix corresponding to each port are determined sequentially. For each sampled vessel, the transport distance corresponding to the non-zero elements in the cargo volume matrix and the container volume matrix is ​​determined based on the cargo volume matrix and the container volume matrix. For each sampled vessel, the cargo volume matrix, the container volume matrix, and the transport distance are used as the voyage survey data corresponding to each sampled vessel.

4. The method according to claim 1, characterized in that, The process involves correcting the origin and destination port information of each sampled vessel in the voyage dataset based on a preset waterway connectivity matrix and port arrival / departure report data, resulting in a first corrected dataset, which includes: Based on the preset waterway connectivity matrix, the origin and destination port information of each sampled vessel in the voyage dataset is compared to determine the voyage data that failed to match. The voyage data that failed to match is matched with the arrival and departure report data to determine the arrival and departure records corresponding to the voyage data that failed to match. Based on the arrival record and the departure record, update the voyage data that failed to match to obtain the updated voyage data; The updated voyage data and the successfully matched voyage data are used as the first corrected dataset.

5. The method according to claim 1, characterized in that, The second corrected dataset is obtained by correcting the transportation distance of each sampled vessel in the first corrected dataset based on the origin and destination port information of each sampled vessel in the first corrected dataset, including: Based on the origin and destination port area information of each sampled vessel in the first corrected dataset, determine the hierarchical origin and destination combination corresponding to the origin and destination port area information; The transport distances corresponding to sampled vessels with the same origin-end point combination at the same level are identified as transport distance groups; The abnormal range of the transport distance group is determined based on the first quartile and the third quartile corresponding to the transport distance group; Each of the transport distances in the transport distance group is compared with the anomaly range, and the transport distances outside the anomaly range are corrected to obtain a second corrected dataset.

6. The method according to claim 5, characterized in that, Based on the origin and destination port information of each sampled vessel in the first corrected dataset, determine the hierarchical origin and destination combinations corresponding to the origin and destination port information, including: Based on the origin and destination port information of each sampled vessel in the first corrected dataset, the vessels are grouped according to the origin and destination port information to obtain the first origin and destination combination. When the number of sampled vessels with the same first origin-end point combination is greater than or equal to a preset threshold, the first origin-end point combination is taken as the hierarchical origin-end point combination corresponding to the origin-end point port area information. When the number of sampled vessels with the same first origin-endpoint combination is less than the preset threshold, they are grouped according to the city where the origin port area and the destination port area belong in the origin-endpoint port area information to obtain the second origin-endpoint combination. When the number of sampled vessels with the same second origin-end point combination is greater than or equal to a preset threshold, the second origin-end point combination is used as the hierarchical origin-end point combination corresponding to the origin-end point port area information. When the number of sampled vessels with the same second origin-endpoint combination is less than a preset threshold, they are grouped according to the provinces to which the origin port area and the destination port area belong in the origin-endpoint port area information to obtain the third origin-endpoint combination. The third origin-endpoint combination is used as the hierarchical origin-endpoint combination corresponding to the origin-endpoint port area information.

7. A device for calculating the flow direction of inland waterway cargo by category, characterized in that, include: The data acquisition module is used to acquire basic voyage survey data or docking survey data corresponding to multiple sampling vessels; The data conversion module is used to determine the voyage survey data corresponding to each sampled vessel based on the multiple ports of call indicated by the berthing survey data, as well as the loading and unloading data corresponding to each port of call. The data merging module is used to establish a voyage dataset based on the basic voyage survey data or the voyage survey data corresponding to each of the sampled vessels. The first correction module is used to correct the origin and destination port information of each sampled vessel in the voyage dataset according to the preset waterway connectivity matrix and port entry and exit report data, so as to obtain the first corrected dataset. The second correction module is used to correct the transportation distance of each sampled vessel in the first correction dataset based on the origin and destination port information of each sampled vessel in the first correction dataset, so as to obtain the second correction dataset. The data extrapolation module is used to determine the cargo turnover and container turnover of each sampled vessel based on the cargo volume, container volume, and transport distance of each sampled vessel in the second corrected dataset; determine the extrapolation factor corresponding to each sampled vessel according to the level corresponding to each sampled vessel; for each type of cargo, the extrapolation factor corresponding to each sampled vessel with the same origin and destination port information is multiplied by the cargo volume to obtain the total cargo volume; for each type of cargo, the extrapolation factor corresponding to each sampled vessel with the same origin and destination port information is multiplied by the container volume to obtain the total container volume; for each type of cargo, the extrapolation factor corresponding to each sampled vessel with the same origin and destination port information is multiplied by the cargo turnover to obtain the total cargo turnover; for each type of cargo, the extrapolation factor corresponding to each sampled vessel with the same origin and destination port information is multiplied by the container turnover to obtain the total container turnover.

8. An electronic device, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the inland waterway cargo classification and flow direction data estimation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the inland waterway cargo classification and flow direction data estimation method according to any one of claims 1 to 6.

Images