Search

CN-121998356-A - Inland river transportation management system based on AI course planning

CN121998356ACN 121998356 ACN121998356 ACN 121998356ACN-121998356-A

Abstract

The invention discloses an inland river transportation management system based on AI (advanced technology interface) course planning, which relates to the technical field of inland river transportation intelligent scheduling and comprises an information aggregation module, an intelligent matching module, a manual auditing module and an AI course planning module. And the information aggregation module receives and stores the cargo source demand and the ship state information. And the intelligent matching module performs association analysis on the cargo source and the ship according to preset rules and by combining with preliminary course evaluation, so as to generate an initial matching scheme set. And the manual auditing module receives the dispatcher instruction, confirms the program and generates the transportation task. And the AI course planning module comprehensively calls inland channel data and real-time environment data based on the confirmed transportation task, and generates a detailed course plan comprising a navigation path, time nodes and energy consumption prediction through dynamic optimization calculation. The invention realizes intelligent coordination of matching and planning links, can generate a navigation scheme which is suitable for real-time environment and has better comprehensive cost, and improves efficiency and economy of inland river transportation scheduling.

Inventors

  • HUANG JUN

Assignees

  • 江苏正沧航运科技有限公司

Dates

Publication Date
20260508
Application Date
20260128

Claims (10)

  1. 1. Inland river transportation management system based on AI programming, characterized by comprising: The information gathering module is used for receiving and storing cargo source demand information uploaded by a cargo owner client and ship state information uploaded by a ship owner client, wherein the cargo source demand information comprises cargo types, origin-destination points, time requirements and cargo transportation capacity, and the ship state information comprises ship positions, load tonnage, navigable states and available time; The intelligent matching module is used for acquiring the cargo source demand information and the ship state information from the information aggregation center, carrying out association analysis on the cargo source and the ship according to a preset matching rule, and generating an initial matching scheme set; The manual auditing module is used for receiving auditing operation instructions of the dispatcher on the initial matching scheme set and generating confirmed transportation tasks according to the auditing operation instructions; and the AI programming module is used for calling inland channel data and real-time environment data to carry out programming calculation based on the confirmed transportation task and generating a detailed programming comprising a navigation path, a predicted time node and energy consumption prediction.
  2. 2. The AI-based programming inland river transportation management system of claim 1, wherein the intelligent matching module comprises: The rule configuration unit is used for storing the preset matching rules, wherein the preset matching rules comprise a load tonnage threshold matching rule, a time window compatibility judging rule and a cargo suitability evaluating rule; The information extraction unit is used for extracting the cargo type, the origin-destination, the time requirement and the freight traffic from the cargo source demand information, and extracting the ship position, the load tonnage, the navigable state and the available time from the ship state information; the matching operation unit is used for inputting the cargo type, the start and stop points, the time requirement and the cargo transportation quantity, the ship position, the load tonnage, the navigable state and the available time into the preset matching rule for calculation and outputting a primarily matched ship list and a matching degree score; The scheme generating unit is used for sorting the preliminarily matched ship list according to the matching degree scores, selecting ships with the matching degree scores higher than a set threshold value to generate the initial matching scheme set, wherein the initial matching scheme set comprises recommended ship identifications, expected cargo rate and time matching degree.
  3. 3. The AI-based programming inland river transportation management system of claim 2, wherein the matching operation unit comprises: The load judging subunit is used for comparing the freight traffic with the load tonnage, calculating the ship load allowance and judging load suitability according to the load tonnage threshold matching rule; The time judging subunit is used for comparing the time requirement with the available time, calculating a time overlapping interval and judging the satisfaction degree of a time window according to the time window compatibility judging rule; The cargo type judging subunit is used for inquiring a preset cargo ship type library suitable for transportation according to the cargo types, comparing the cargo type library with the current ship type and judging the adaptation level of the cargo and the ship according to the cargo suitability evaluation rule; And the comprehensive scoring subunit is used for carrying out weighted fusion calculation on the load suitability, the satisfaction degree of the time window and the suitability level of the goods and the ships and generating the matching degree score for each ship.
  4. 4. The AI-programming-based inland river transportation management system of claim 1, wherein the AI programming module comprises: The data acquisition unit is used for acquiring the origin-destination information in the confirmed transportation task, synchronously acquiring the channel hydrological data, the ship lock distribution data and the bridge clearance data in the inland channel database, and acquiring real-time hydrological meteorological data from an external environment interface; the path planning unit is used for calculating a plurality of candidate navigation paths through a preset path searching algorithm based on the origin-destination information, the navigation channel hydrological data, the ship lock distribution data, the bridge clearance data and the real-time hydrological meteorological data; The evaluation optimization unit is used for calculating the comprehensive cost of the path according to a preset evaluation model for each candidate navigation path, wherein the comprehensive cost comprises navigation time cost, energy consumption cost and risk cost, and selecting the candidate navigation path with the lowest comprehensive cost as the optimal navigation path; and the plan generating unit is used for calculating a time node for predicting the key navigation point to be reached and an energy consumption predicted value in the whole course in the navigation process according to the optimal navigation path and combining a ship performance model, and integrating and generating the detailed navigation plan.
  5. 5. The AI-based programming inland river transportation management system of claim 4, wherein the evaluation optimization unit comprises: A time cost calculation subunit, configured to calculate the navigation time cost according to the length of the preferred navigation path, the water flow speed in the channel hydrologic data, the estimated lock passing waiting time in the lock distribution data, and the still water speed in the ship performance model; The energy consumption cost calculation subunit is used for calculating the energy consumption cost according to the length of the optimal navigation path, the water flow speed and the water flow direction in the navigation channel hydrologic data, the main engine oil consumption characteristic curve in the ship performance model and combining the wind direction and the wind speed in the real-time hydrologic data; the risk cost calculation subunit is used for evaluating navigation risk and quantitatively generating the risk cost according to the relationship between the bridge clearance data and the draft and height of the ship, the shoal and dangerous beach distribution information in the channel hydrologic data and the visibility and wind power level in the real-time hydrologic meteorological data; and the cost fusion subunit is used for linearly combining the navigation time cost, the energy consumption cost and the risk cost according to preset weights, and calculating to obtain the comprehensive cost of each candidate navigation path.
  6. 6. The AI-based programming inland river transportation management system of claim 1, wherein the system further comprises: The task execution monitoring module is used for receiving the real-time position information reported by the ship positioning device in the execution process of the transportation task, comparing the real-time position information with the predicted time node in the detailed voyage plan and generating a voyage state deviation report; and the dynamic re-planning triggering module is used for sending a re-planning request to the AI programming engine when the deviation value in the navigation state deviation report exceeds a preset tolerance threshold, wherein the re-planning request comprises the current ship position and the task residual path.
  7. 7. The AI-based programming inland transportation management system of claim 6, wherein the task performance monitoring module comprises: A data receiving subunit, configured to continuously receive the real-time position information and the ship status report from the ship positioning device; The comparison and analysis subunit is used for extracting a predicted time node and a predicted position corresponding to the current navigation segment from the detailed navigation path plan, comparing the predicted time node and the predicted position with the real-time position information and the current system time, and calculating a time deviation value and a position deviation distance; and the report generation subunit is used for generating the navigation state deviation report comprising deviation grade, deviation reason speculation and influence assessment according to the time deviation value and the position deviation distance and by combining with a preset navigation state assessment rule.
  8. 8. The AI-programming-based inland transportation management system of claim 7, wherein the dynamic re-programming trigger module comprises: the threshold judging subunit is used for reading the time deviation value and the position deviation distance in the navigation state deviation report and comparing the time deviation value and the position deviation distance with preset tolerance thresholds related to time and distance respectively; A request generation subunit, configured to generate the re-planning request when any one of the time deviation value or the position deviation distance exceeds a corresponding tolerance threshold, where the re-planning request encapsulates a current ship position, a task destination, remaining cargo information, and a latest real-time environmental data request instruction; and the instruction sending subunit is used for sending the re-programming request to the AI programming engine and triggering the AI programming engine to start a new round of programming calculation based on the current state.
  9. 9. The AI-based programming inland river transportation management system of claim 1, wherein the system further comprises: The data feedback and learning module is used for collecting the detailed voyage plan, the actual voyage track data, the actual energy consumption data and the voyage state deviation report of the completed transport task; And the model optimization unit is used for comparing and analyzing the predicted data in the detailed voyage plan with the actual voyage track data and the actual energy consumption data, calculating a predicted error, and carrying out iterative optimization on parameters of a ship performance model and an evaluation model used in the AI voyage planning engine by utilizing the predicted error.
  10. 10. The AI-based programming inland river transportation management system of claim 9, wherein the model optimization unit comprises: The error calculation subunit is used for extracting the predicted time node and the energy consumption predicted value in the detailed voyage plan aiming at each completed transportation task, and carrying out point-by-point comparison on the predicted time node and the energy consumption predicted value extracted from the actual voyage track data and the actual energy consumption value extracted from the actual energy consumption data to generate a time prediction error sequence and an energy consumption prediction error sequence; The parameter adjustment subunit is used for adjusting the navigation speed-resistance relation parameter in the ship performance model and the calculation weight of the time cost and the energy consumption cost in the evaluation model by adopting a gradient descent algorithm according to the time prediction error sequence and the energy consumption prediction error sequence; and the model updating subunit is used for updating the adjusted parameters to the model corresponding to the AI programming engine and calculating the programming of the subsequent transportation task.

Description

Inland river transportation management system based on AI course planning Technical Field The invention belongs to the technical field of intelligent scheduling of inland river transportation, and particularly relates to an inland river transportation management system based on AI (advanced technology engineering) course planning. Background In current inland-river cargo transportation management, the problem of asymmetry of cargo source and transport capacity information is common. The existing information platform mainly realizes release and display of cargo source and ship information, and the matching function is mostly based on small amount of static rules such as ship tonnage, position and the like. The matching mode is disjointed with the execution of the follow-up actual sailing task, and key factors such as route feasibility, sailing cost and the like are not fully considered during matching, so that the generated matching scheme often faces adjustment or even cannot be executed in the follow-up actual scheduling, and the overall scheduling efficiency is low. Traditional voyage planning relies heavily on the individual experience of the captain or uses simple electronic voyage diagrams for path finding. Such methods cannot systematically incorporate environmental data that varies in real time, such as water level, flow rate, weather conditions, etc. The planning result is often a static and ideal path, and the dynamic optimal balance among the sailing time, the fuel consumption and the sailing safety cannot be realized in the actual sailing, and the strain capacity is lacked when the planning result faces sudden hydrological weather conditions or temporary control of the sailing channel. The technical scheme is needed, cargo ship matching and voyage depth planning can be organically coordinated, and multisource and dynamic channel and environment constraints can be accurately processed in planning, so that a truly executable transport task scheme with optimal comprehensive cost is output. Disclosure of Invention The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an AI-based voyage planning inland river transportation management system comprising: The information gathering module is used for receiving and storing cargo source demand information uploaded by a cargo owner client and ship state information uploaded by a ship owner client, wherein the cargo source demand information comprises cargo types, origin-destination points, time requirements and cargo transportation capacity, and the ship state information comprises ship positions, load tonnage, navigable states and available time; The intelligent matching module is used for acquiring the cargo source demand information and the ship state information from the information aggregation center, carrying out association analysis on the cargo source and the ship according to a preset matching rule, and generating an initial matching scheme set; The manual auditing module is used for receiving auditing operation instructions of the dispatcher on the initial matching scheme set and generating confirmed transportation tasks according to the auditing operation instructions; and the AI programming module is used for calling inland channel data and real-time environment data to carry out programming calculation based on the confirmed transportation task and generating a detailed programming comprising a navigation path, a predicted time node and energy consumption prediction. Preferably, the intelligent matching module includes: The rule configuration unit is used for storing the preset matching rules, wherein the preset matching rules comprise a load tonnage threshold matching rule, a time window compatibility judging rule and a cargo suitability evaluating rule; The information extraction unit is used for extracting the cargo type, the origin-destination, the time requirement and the freight traffic from the cargo source demand information, and extracting the ship position, the load tonnage, the navigable state and the available time from the ship state information; the matching operation unit is used for inputting the cargo type, the start and stop points, the time requirement and the cargo transportation quantity, the ship position, the load tonnage, the navigable state and the available time into the preset matching rule for calculation and outputting a primarily matched ship list and a matching degree score; The scheme generating unit is used for sorting the preliminarily matched ship list according to the matching degree scores, selecting ships with the matching degree scores higher than a set threshold value to generate the initial matching scheme set, wherein the initial matching scheme set comprises recommended ship identifications, expected cargo rate and time matching degree. Preferably, the matching operation unit includes: The load judging subunit is