Transportation track monitoring method and device, equipment and storage medium

Abstract

The invention relates to the technical field of track monitoring, in particular to a transportation track monitoring method, device and equipment and a storage medium, and the method comprises the steps: obtaining vehicle sensor information, and carrying out decryption and decompression processing to obtain decryption information; judging whether an abnormal condition of road congestion exists according to the decryption information and the obtained vehicle information, and if so, confirming a real-time position according to the decryption information and obtaining real-time congestion information; inputting the obtained real-time time, real-time position and real-time congestion information into a traffic prediction model to obtain traffic prediction information; inputting the decryption information and the traffic prediction information into a traffic influence evaluation model to obtain traffic influence evaluation information; processing a directed graph constructed based on the vehicle information and the influence evaluation information by combining a graph theory algorithm and a heuristic search strategy to obtain an optimized path; according to the method disclosed by the invention, the vehicle sensor information is integrated to realize the acquisition of the real-time position and the generation of the optimized path, and the monitoring efficiency of the transportation track is improved.

Description

Technical Field

[0001] The present invention relates to the field of track monitoring technology, and in particular to a transport track monitoring method, device, equipment and storage medium. Background Art

[0002] The traditional monitoring mode of logistics transportation trajectory is: manual records and GPS positioning system complement each other. This monitoring strategy has indeed promoted the improvement of logistics management efficiency to a certain extent in the past; however, with the vigorous development of the logistics industry and its continuous expansion, as well as the increasingly complex trend of logistics operations, the limitations of the monitoring mode based on manual records have become increasingly obvious, and it is difficult to meet the modern efficient and accurate management needs.

[0003] Manual recording of positioning information has the disadvantages of being cumbersome and time-consuming, requiring a large amount of human resources, increasing the operating costs of logistics companies, and the presence of human factors in the manual recording process makes it easy for errors and omissions to occur, which in turn affects the accuracy and reliability of the data; on the other hand, although the GPS positioning system provides strong technical support for logistics monitoring and can achieve real-time tracking and monitoring of the location of goods, it also has many limitations; for example, the coverage of GPS signals is not perfect, especially in remote areas or complex terrain conditions, the signal is easily interfered or interrupted, resulting in the inability to transmit and update data in a timely manner; in addition, the data transmission speed is also affected by many factors, such as network conditions, equipment performance, etc., which will affect the real-time and accuracy of the collected data, thereby affecting the update effect of the real-time logistics transportation trajectory.

[0004] That is, traditional monitoring strategies have problems such as delayed updates of logistics transportation trajectories, incorrect update information, and high update costs.

[0005] It can be seen that the existing technology still needs to be improved and enhanced. Summary of the invention

[0006] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a transportation trajectory monitoring method, which has the advantages of timely transportation trajectory monitoring and accurate monitoring results, and can generate an optimized path, provide data support for logistics transportation trajectory optimization, and improve logistics transportation efficiency.

[0007] The first aspect of the present invention provides a transport trajectory monitoring method, comprising: obtaining vehicle information of a transport vehicle, and obtaining vehicle sensor information corresponding to the transport vehicle, decrypting and decompressing the vehicle sensor information to obtain decrypted information; judging whether there is an abnormal situation based on the decrypted information and the vehicle information, and if there is an abnormal situation, generating an abnormal reporting instruction; when the abnormal situation is road congestion, confirming the real-time position of the transport vehicle based on the decrypted information, and obtaining real-time congestion information based on the real-time position; obtaining real-time time, inputting the real-time time, the real-time position and the real-time congestion information into a pre-constructed traffic prediction model to obtain traffic prediction information; inputting the decrypted information and the traffic prediction information into a pre-constructed traffic impact assessment model to obtain traffic impact assessment information; constructing a directed graph based on the vehicle information and the impact assessment information, and generating an optimized path based on the constructed directed graph in combination with a graph theory algorithm and a heuristic search strategy.

[0008] Optionally, in a first implementation method of the first aspect of the present invention, the vehicle information of the transport vehicle is obtained, and the vehicle sensor information corresponding to the transport vehicle is obtained, and the vehicle sensor information is decrypted and decompressed to obtain the decrypted information, including: obtaining vehicle information, the vehicle information including driver information, vehicle model information and vehicle line information, the vehicle line information including a transport route, a starting point, multiple way points and a receipt point; based on the license plate information, obtaining the vehicle sensor information corresponding to the transport vehicle, the vehicle sensor information including on-board GPS information, temperature and humidity information and acceleration information; obtaining key information, decrypting the vehicle sensor information based on the key information and the decryption algorithm, and according to the compressed file type of the vehicle sensor information, using corresponding compression software to decompress the vehicle sensor information to obtain the decrypted information; backing up the vehicle information, the vehicle sensor information and the decrypted information to a pre-selected backup storage node.

[0009] Optionally, in a second implementation method of the first aspect of the present invention, the determination of whether there is an abnormal situation based on the decrypted information and the vehicle information, and generating an abnormal reporting instruction if there is an abnormal situation, includes: confirming whether the transport vehicle has abnormal acceleration or abnormal deceleration based on the acceleration information; confirming the real-time position of the transport vehicle based on the on-board GPS information, and comparing the real-time position with the vehicle lane information to determine whether there is abnormal deviation; continuously acquiring the on-board GPS information within a preset monitoring period to determine whether there is abnormal parking; when there is abnormal acceleration, abnormal deceleration, abnormal deviation or abnormal parking, generating a corresponding abnormal reporting instruction according to the abnormality type.

[0010] Optionally, in a third implementation method of the first aspect of the present invention, when the abnormal situation is road congestion, the real-time position of the transport vehicle is confirmed according to the decrypted information, and real-time congestion information is obtained according to the real-time position, including: when abnormal deceleration and abnormal stopping problems occur, determine whether there is a road congestion problem; if there is a road congestion problem, confirm the real-time position of the transport vehicle according to the vehicle GPS information, and the real-time position is the real-time longitude and latitude coordinates; according to the real-time position, use the map service API to obtain real-time congestion information, and the real-time congestion information includes real-time road section information, congestion degree and expected travel time.

[0011] Optionally, in a fourth implementation method of the first aspect of the present invention, the real-time time is obtained, and the real-time time, the real-time location and the real-time congestion information are input into a pre-built traffic prediction model to obtain traffic prediction information, including: format conversion processing of the real-time time, the real-time location information and the real-time congestion information to obtain standard data; judging whether the real-time time is a special time, the special time includes morning rush hour, evening rush hour and holidays; when the real-time time is a special time, obtaining an impact weight corresponding to the real-time time; inputting the standard data and the impact weight into a traffic prediction model pre-built based on a CNN convolutional neural network to obtain traffic prediction information, wherein the traffic prediction information is the traffic conditions within a certain time period.

[0012] Optionally, in a fifth implementation method of the first aspect of the present invention, the decrypted information and the traffic forecast information are input into a pre-built traffic impact assessment model to obtain traffic impact assessment information, including: using a meteorological service API to obtain weather change information corresponding to the real-time time and the real-time location; performing format conversion processing on the temperature and humidity information included in the decrypted information to obtain standard temperature and humidity information; generating actual weather information corresponding to the real-time time and the real-time location based on the weather change information and the standard temperature and humidity information; and inputting the actual weather information and the traffic forecast information into a pre-built traffic impact assessment model based on a multiple linear regression method to obtain traffic impact assessment information.

[0013] Optionally, in a sixth implementation method of the first aspect of the present invention, a directed graph is constructed based on the vehicle information and the impact assessment information, and an optimized path is generated based on the constructed directed graph in combination with a graph theory algorithm and a heuristic search strategy, including: converting the vehicle model information, the vehicle line information and the evaluation information into nodes and edges of a directed graph, and defining a weight function for the converted edges; using the Dijkstra algorithm to search for possible paths connecting the starting point and the transceiver point, and during the search process, introducing a greedy best priority search strategy, and using a heuristic function to optimize the search process; when the number of searches for possible paths reaches a preset number of iterations, an optimized path is obtained; based on the optimized path and the vehicle line information, a map API is used to generate a route change comparison diagram, and push information is generated based on the route change comparison diagram and the driver information.

[0014] The second aspect of the present invention provides a transport trajectory monitoring device, including: a decompression and decryption module, which is used to obtain vehicle information of the transport vehicle, and obtain vehicle sensor information corresponding to the transport vehicle, and decrypt and decompress the vehicle sensor information to obtain decrypted information; an abnormality judgment module, which is used to judge whether there is an abnormal situation based on the decrypted information and vehicle information, and if there is an abnormal situation, generate an abnormality reporting instruction; an acquisition module, which is used to confirm the real-time position of the transport vehicle according to the decrypted information when the abnormal situation is road congestion, and obtain real-time congestion information according to the real-time position; a prediction module, which is used to obtain real-time time, input the real-time time, the real-time position and the real-time congestion information into a pre-constructed traffic prediction model to obtain traffic prediction information; an evaluation module, which is used to input the decrypted information and the traffic prediction information into a pre-constructed traffic impact evaluation model to obtain traffic impact evaluation information; a generation module, which is used to construct a directed graph based on the vehicle information and the impact evaluation information, and generate an optimized path based on the constructed directed graph in combination with a graph theory algorithm and a heuristic search strategy.

[0015] Optionally, in a first implementation method of the second aspect of the present invention, the decryption and decompression module includes: a first acquisition unit, used to acquire vehicle information, the vehicle information including driver information, vehicle model information and vehicle line information, the vehicle line information including a transportation route, a starting point, multiple waypoints and a signing point; a second acquisition unit, used to acquire vehicle sensor information corresponding to the transport vehicle based on the license plate information, the vehicle sensor information including on-board GPS information, temperature and humidity information and acceleration information; a decryption and decompression unit, used to acquire key information, decrypt the vehicle sensor information based on the key information and the decryption algorithm, and according to the compressed file type of the vehicle sensor information, use corresponding compression software to decompress the vehicle sensor information to obtain decrypted information; a backup unit, used to back up the vehicle information, the vehicle sensor information and the decrypted information to a pre-selected backup storage node.

[0016] Optionally, in a second implementation method of the second aspect of the present invention, the abnormal judgment module includes: a first judgment unit, used to confirm whether the transport vehicle has abnormal acceleration or abnormal deceleration based on acceleration information; a second judgment unit, used to confirm the real-time position of the transport vehicle based on the on-board GPS information, and compare the real-time position with the vehicle lane information to determine whether there is abnormal deviation; a third judgment unit, used to continuously obtain the on-board GPS information within a preset monitoring period to determine whether there is abnormal parking; an abnormal reporting unit, used to generate a corresponding abnormal reporting instruction according to the abnormality type when there is abnormal acceleration, abnormal deceleration, abnormal deviation or abnormal parking.

[0017] Optionally, in a third implementation method of the second aspect of the present invention, the acquisition module includes: a fourth judgment unit, used to determine whether there is a road congestion problem when abnormal deceleration and abnormal stopping problems occur; a confirmation unit, used to confirm the real-time position of the transport vehicle according to the vehicle GPS information if there is a road congestion problem, and the real-time position is the real-time latitude and longitude coordinates; a third acquisition unit, used to obtain real-time congestion information using a map service API according to the real-time position, and the real-time congestion information includes real-time road section information, congestion degree and estimated travel time.

[0018] Optionally, in a fourth implementation method of the second aspect of the present invention, the prediction module includes: a first conversion unit, used to perform format conversion processing on the real-time time, the real-time location information and the real-time congestion information to obtain standard data; a fifth judgment unit, used to judge whether the real-time time is a special time, and the special time includes morning rush hour, evening rush hour and holidays; a fourth acquisition unit, used to obtain the impact weight corresponding to the real-time time when the real-time time is a special time; a prediction unit, used to input the standard data and the impact weight into a traffic prediction model pre-built based on a CNN convolutional neural network to obtain traffic prediction information, and the traffic prediction information is the traffic conditions within a certain time period.

[0019] Optionally, in a fifth implementation of the second aspect of the present invention, the evaluation module includes: a fifth acquisition unit, used to use a meteorological service API to obtain weather change information corresponding to the real-time time and the real-time location; a second conversion unit, used to perform format conversion processing on the temperature and humidity information included in the decrypted information to obtain standard temperature and humidity information; a first generation unit, used to generate actual weather information corresponding to the real-time time and the real-time location based on the weather change information and the standard temperature and humidity information; an evaluation unit, used to input the actual weather information and the traffic forecast information into a traffic impact assessment model pre-constructed based on a multivariate linear regression method to obtain traffic impact assessment information.

[0020] Optionally, in a sixth implementation manner of the second aspect of the present invention, the generation module includes: a third conversion unit, used to convert the vehicle model information, the vehicle line information and the evaluation information into nodes and edges of a directed graph, and define a weight function for the converted edges; a search unit, used to use the Dijkstra algorithm to search for possible paths connecting the starting point and the sending and receiving points. During the search process, a greedy best priority search strategy is introduced, and the search process is optimized using a heuristic function; an output unit, used to obtain an optimized path when the number of searches for possible paths reaches a preset number of iterations; a second generation unit, used to generate a route change comparison diagram based on the optimized path and vehicle line information using a map API, and generate push information based on the route change comparison diagram and the driver information.

[0021] A third aspect of the present invention provides a transport trajectory monitoring device, which includes: a memory and at least one processor, wherein instructions are stored in the memory; at least one of the processors calls the instructions in the memory so that the transport trajectory monitoring device executes each step of the transport trajectory monitoring method described in any one of the above items.

[0022] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, and when the instructions are executed by a processor, the various steps of any of the above-mentioned transport trajectory monitoring methods are implemented.

[0023] In the technical solution of the present invention, decrypted information is obtained by acquiring vehicle sensor information and performing decryption and decompression processing; whether there is an abnormal situation of road congestion is determined based on the decrypted information and the acquired vehicle information, and if so, the real-time position is confirmed based on the decrypted information and the real-time congestion information is acquired; the acquired real-time time, real-time position and real-time congestion information are input into the traffic prediction model to obtain traffic prediction information; the decrypted information and traffic prediction information are input into the traffic impact assessment model to obtain traffic impact assessment information; the directed graph constructed based on the vehicle information and the impact assessment information is processed in combination with the graph theory algorithm and the heuristic search strategy to obtain the optimized path; the method disclosed in the present application integrates the vehicle sensor information to realize the acquisition of the real-time position and the generation of the optimized path, can realize the real-time update of the transportation trajectory, and has the advantages of high accuracy and reliability of the update result, reducing the cost waste caused by information asymmetry; further, the generated optimized path can provide data support for the optimization of the transportation trajectory, greatly improving the logistics transportation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A first flow chart of the transport trajectory monitoring method provided by an embodiment of the present invention;

[0025] Figure 2A second flow chart of the transport trajectory monitoring method provided by an embodiment of the present invention;

[0026] Figure 3 A third flow chart of the transport trajectory monitoring method provided by an embodiment of the present invention;

[0027] Figure 4 A fourth flow chart of the transport trajectory monitoring method provided by an embodiment of the present invention;

[0028] Figure 5 A fifth flow chart of the transport trajectory monitoring method provided by an embodiment of the present invention;

[0029] Figure 6 A sixth flow chart of the transport trajectory monitoring method provided by an embodiment of the present invention;

[0030] Figure 7 A seventh flow chart of the transport trajectory monitoring method provided by an embodiment of the present invention;

[0031] Figure 8 A schematic diagram of the structure of a transport track monitoring device provided by an embodiment of the present invention;

[0032] Fig. 9 A schematic diagram of the structure of a transport trajectory monitoring device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The present invention provides a method, device, equipment and storage medium for monitoring a transport trajectory. In the present invention, the terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the transportation trajectory monitoring method in the embodiment of the present invention includes:

[0035] 101. Acquire vehicle information of the transport vehicle, acquire vehicle sensor information corresponding to the transport vehicle, decrypt and decompress the vehicle sensor information, and obtain decrypted information;

[0036] In this embodiment, by acquiring the vehicle information and vehicle sensor information of the transport vehicle, the vehicle status can be monitored in real time and abnormal situations can be discovered in time. The combination of the wide-range GPS positioning system and the small-range vehicle sensor information improves the accuracy and reliability of the collected location information.

[0037] 102. Determine whether there is an abnormal situation based on the decrypted information and the vehicle information, and if there is an abnormal situation, generate an abnormality reporting instruction;

[0038] In this embodiment, when an abnormal situation occurs, an abnormal reporting instruction can be generated in time to achieve timely warning and processing of the abnormal situation, thereby improving the stability of the logistics transportation process.

[0039] 103. When the abnormal situation is road congestion, the real-time location of the transport vehicle is confirmed based on the decrypted information, and the real-time congestion information is obtained based on the real-time location;

[0040] In this embodiment, when road congestion is detected, the real-time position of the transport vehicle can be confirmed and real-time congestion information can be obtained to provide data support for subsequent route optimization.

[0041] 104. Acquire real time, and input the real time, the real location, and the real-time congestion information into a pre-built traffic prediction model to obtain traffic prediction information;

[0042] 105. Input the decrypted information and the traffic prediction information into a pre-built traffic impact assessment model to obtain traffic impact assessment information;

[0043] 106. A directed graph is constructed based on vehicle information and impact assessment information, and an optimized path is generated based on the constructed directed graph by combining graph theory algorithms and heuristic search strategies.

[0044] In this embodiment, traffic impact assessment information is obtained based on traffic prediction information and decrypted information, and an optimized path is generated based on vehicle information and traffic impact assessment information, which can provide data support for path adjustment, improve transportation efficiency and reduce transportation costs.

[0045] The present application discloses a method for monitoring a transport trajectory, which obtains decrypted information by acquiring vehicle sensor information and performing decryption and decompression processing; determines whether there is an abnormal situation of road congestion based on the decrypted information and the acquired vehicle information, and if so, confirms the real-time position and acquires the real-time congestion information based on the decrypted information; inputs the acquired real-time time, real-time position and real-time congestion information into a traffic prediction model to acquire traffic prediction information; inputs the decrypted information and traffic prediction information into a traffic impact assessment model to acquire traffic impact assessment information; combines a graph theory algorithm and a heuristic search strategy to process a directed graph constructed based on vehicle information and impact assessment information to acquire an optimized path; the method disclosed in the present application integrates vehicle sensor information to realize the acquisition of real-time position and the generation of an optimized path, can realize real-time update of the transport trajectory, and has the advantages of high accuracy and reliability of the update result, reducing the cost waste caused by information asymmetry; further, the generated optimized path can provide data support for transport trajectory optimization, greatly improving logistics transportation efficiency.

[0046] See also Figure 2 , a second embodiment of the method for monitoring the transport trajectory in the embodiment of the present invention includes:

[0047] 201. Obtain vehicle information, wherein the vehicle information includes driver information, vehicle model information, and vehicle route information, wherein the vehicle route information includes a transportation route, a starting point, multiple passing points, and a signing point;

[0048] In this embodiment, the driver information includes the driver's identity information and contact mobile phone number; the vehicle model information includes the license plate number, vehicle type and vehicle load capacity.

[0049] 202. Based on the license plate information, obtain vehicle sensor information corresponding to the transport vehicle, wherein the vehicle sensor information includes vehicle-mounted GPS information, temperature and humidity information, and acceleration information;

[0050] 203. Acquire key information, decrypt the vehicle sensor information based on the key information and the decryption algorithm, and decompress the vehicle sensor information using corresponding compression software according to the compressed file type of the vehicle sensor information to obtain decrypted information;

[0051] In this embodiment, key information for decrypting vehicle sensor information is obtained from an authorized key management system for decryption processing; for decompression processing, for example, assuming that the type of the compressed file recording the vehicle sensor information is a zip file, it can be decompressed using compression software such as WinRAR, 7-Zip, etc.

[0052] In this embodiment, by using key information and decryption algorithms, the security of vehicle sensor data during transmission and storage is ensured to prevent unauthorized access; the decryption and decompression process ensures the integrity and accuracy of the data, avoids possible damage or tampering of the data during transmission, and improves the reliability and security of the data transmission process.

[0053] 204. Back up the vehicle information, the vehicle sensor information, and the decryption information to a pre-selected backup storage node.

[0054] In this embodiment, the redundancy of key data is ensured by backing up vehicle information, vehicle sensor information and decryption information to a backup storage node, so that when the main storage node fails, it can quickly switch to the backup node to ensure the continuous availability of data. The backup mechanism increases the fault tolerance of the system and reduces the risk of data loss due to hardware failure, software errors or external attacks, thereby improving the reliability of the entire system during operation.

[0055] See also Figure 3 , a third embodiment of the method for monitoring the transport trajectory in the embodiment of the present invention includes:

[0056] 301. Determine whether the transport vehicle has abnormal acceleration or abnormal deceleration according to the acceleration information;

[0057] In this embodiment, a threshold range of normal acceleration is preset, and the threshold range can be determined based on the performance parameters of the transport vehicle and the driving environment; the actually collected acceleration data is compared with the preset threshold range, and when the acceleration data exceeds the threshold range, that is, the acceleration of the vehicle suddenly increases or decreases, it can be considered that the vehicle has abnormal acceleration or deceleration.

[0058] 302. Confirm the real-time position of the transport vehicle according to the vehicle-mounted GPS information, and compare the real-time position with the vehicle line information to determine whether there is an abnormal deviation;

[0059] In this embodiment, a geographic information system (GIS) algorithm is used in combination with path planning and matching technology to compare and analyze the real-time acquired vehicle-mounted GPS information and the vehicle lane information. When the deviation between the actual position of the vehicle and the vehicle lane information exceeds a preset yaw threshold, it is judged as abnormal yaw.

[0060] 303. During the preset monitoring time, the vehicle GPS information is continuously obtained to determine whether there is any abnormal stop;

[0061] In this embodiment, the preset monitoring time may be 5 minutes. When the vehicle-mounted GPS information continuously acquired within 5 minutes indicates that the transport vehicle has not moved, there is an abnormal parking problem.

[0062] 304. When there is abnormal acceleration, abnormal deceleration, abnormal deviation or abnormal stopping, a corresponding abnormal reporting instruction is generated according to the abnormal type.

[0063] In this embodiment, by real-time monitoring and responding to abnormal conditions in vehicle operation, such as acceleration, deceleration, deviation or stopping, the system can quickly generate and report corresponding abnormal instructions, so as to take timely measures to ensure the safety and reliability of vehicle operation, reduce the probability of accidents, and improve the operational efficiency of logistics companies.

[0064] See also Figure 4 , a fourth embodiment of the method for monitoring the transport trajectory in the embodiment of the present invention includes:

[0065] 401. When abnormal deceleration and abnormal stopping occur, determine whether there is a road congestion problem;

[0066] In this embodiment, when abnormal deceleration and abnormal stopping problems occur, it can be confirmed through the map service API whether there is a road congestion problem.

[0067] 402. If there is a road congestion problem, confirm the real-time position of the transport vehicle according to the vehicle GPS information, where the real-time position is the real-time latitude and longitude coordinates;

[0068] 403. According to the real-time location, use a map service API to obtain real-time congestion information, where the real-time congestion information includes real-time road section information, congestion degree, and estimated travel time.

[0069] See also Figure 5 , a fifth embodiment of the method for monitoring the transport trajectory in the embodiment of the present invention includes:

[0070] 501. Perform format conversion processing on the real-time time, the real-time location information, and the real-time congestion information to obtain standard data;

[0071] In this embodiment, the collected real-time time can be parsed through the transportation trajectory monitoring tool to ensure that it conforms to the standard time format; further, the real-time location information is formatted to ensure that it conforms to the standard format of the geographic information system (GIS); further, the real-time congestion information is classified and encoded and converted into a standard traffic congestion level or numerical representation.

[0072] 502. Determine whether the real-time time is a special time, where the special time includes a morning peak, an evening peak, and holidays;

[0073] In this embodiment, the current real-time time is obtained, and the calendar check is used to confirm whether the current date is a weekday or a holiday; if it is a weekday, it is further determined whether the current time is in the morning rush hour or evening rush hour period, and if it is a holiday, it is directly determined as a special time; for the morning rush hour, it is usually defined as the time period between 7 am and 9 am, and for the evening rush hour, it is usually defined as the time period between 5 pm and 7 pm.

[0074] 503. When the real-time time is a special time, obtaining an influence weight corresponding to the real-time time;

[0075] In this embodiment, the influence weight corresponding to the real time is determined according to a preset weight calculation rule.

[0076] 504. Input the standard data and the influence weight into a traffic prediction model pre-built based on a CNN convolutional neural network to obtain traffic prediction information, where the traffic prediction information is the traffic conditions within a certain time period.

[0077] In this embodiment, the advantages of CNN convolutional neural network in image recognition and transportation trajectory monitoring are utilized to combine standard data and influence weights to improve the accuracy of traffic forecasting; by inputting real-time or historical traffic data, the traffic forecasting model can learn and identify the patterns and trends of traffic flow, thereby predicting traffic conditions within a certain period of time in the future; it can provide valuable reference information for the optimization of logistics transportation routes, help alleviate traffic congestion, optimize traffic flow, and improve road use efficiency.

[0078] See also Figure 6 The sixth embodiment of the method for monitoring the transport trajectory in the embodiment of the present invention includes:

[0079] 601. Use the weather service API to obtain weather change information corresponding to the real-time time and real-time location;

[0080] 602. Perform format conversion processing on the temperature and humidity information included in the decrypted information to obtain standard temperature and humidity information;

[0081] In this embodiment, the temperature and humidity information is formatted for conversion to ensure that the temperature is expressed in degrees Celsius and the humidity is expressed in %.

[0082] 603. Generate actual weather information corresponding to the real-time time and the real-time location according to the weather change information and the standard temperature and humidity information;

[0083] In this embodiment, weather change information is obtained through the OpenWeatherMap meteorological service API, and preset weather temperature and humidity corresponding information is obtained, and the weather temperature and humidity corresponding information is the temperature and humidity reference value corresponding to the weather; the weather change information and the standard temperature and humidity information are compared and analyzed with the weather temperature and humidity corresponding information to obtain the actual weather information.

[0084] 604. Input the actual weather information and the traffic forecast information into a traffic impact assessment model pre-constructed based on a multiple linear regression method to obtain traffic impact assessment information.

[0085] In this embodiment, by combining actual weather information and traffic forecast information, the traffic impact model can more accurately predict traffic conditions under specific conditions, thereby providing a reliable basis for optimizing path planning; the multivariate linear regression method allows multiple influencing factors to be considered simultaneously, which helps to reveal the relative importance of different factors on traffic impacts, and provides deeper insights for optimizing path planning. It can also identify potential traffic bottlenecks and risk points, thereby taking preventive maintenance measures to reduce the occurrence of accidents and congestion and improve logistics and transportation efficiency.

[0086] See also Figure 7 The seventh embodiment of the method for monitoring the transport trajectory in the embodiment of the present invention includes:

[0087] 701. Convert the vehicle model information, the vehicle lane information, and the evaluation information into nodes and edges of a directed graph, and define a weight function for the converted edges;

[0088] In this embodiment, the vehicle model is defined as a node, the vehicle line is also defined as a node, and the evaluation information can be used as an attribute or label of the node; based on the relationship between the vehicle model and the vehicle line and the evaluation information, the directed edges between the nodes are defined; and a weight function is defined for each edge, and the weight function calculates the weight of the edge according to the evaluation information; the weight can reflect the matching degree, efficiency, cost or other relevant evaluation indicators between the vehicle model and the vehicle line.

[0089] 702. Use Dijkstra algorithm to search for possible paths connecting the starting point and the sending and receiving points. During the search process, introduce the greedy best-first search strategy and use the heuristic function to optimize the search process.

[0090] In this embodiment, the path search process is optimized by combining the Dijkstra algorithm and the greedy best-first search strategy, as well as the use of the heuristic function; the Dijkstra algorithm can ensure that the shortest path is found, while the greedy best-first search strategy helps to quickly narrow the search range and reduce unnecessary calculations; the introduction of the heuristic function further guides the search process, allowing the algorithm to select paths more intelligently, thereby improving search efficiency and reducing the consumption of computing resources.

[0091] 703. When the number of possible path searches reaches a preset number of iterations, an optimized path is obtained;

[0092] 704. Based on the optimized path and the vehicle line information, a route change comparison diagram is generated using a map API, and push information is generated based on the route change comparison diagram and the driver information.

[0093] In this embodiment, the optimized route is compared with the original route using Google Maps API, the differences between the two are analyzed, such as distance, estimated time, cost, etc., and a route change comparison map is generated; the driver information includes the driver's mobile phone number, and the route change comparison map and the new estimated arrival time are integrated to generate push information, and the push information is pushed to the driver's mobile phone in the form of text messages; by timely pushing the change comparison map, the logistics transportation efficiency can be improved, delays caused by poor traffic conditions can be reduced, and the driver can be helped to avoid congested areas, saving fuel and time.

[0094] The above describes the method for monitoring the transport track in the embodiment of the present invention. The following describes the device for monitoring the transport track in the embodiment of the present invention. Figure 8 , an embodiment of the transport track monitoring device in the embodiment of the present invention includes:

[0095] The decompression and decryption module 801 is used to obtain the vehicle information of the transport vehicle, and obtain the vehicle sensor information corresponding to the transport vehicle, decrypt and decompress the vehicle sensor information to obtain the decrypted information; the abnormality judgment module 802 is used to judge whether there is an abnormal situation based on the decrypted information and the vehicle information, and if there is an abnormal situation, generate an abnormality reporting instruction; the acquisition module 803 is used to confirm the real-time position of the transport vehicle according to the decrypted information when the abnormal situation is road congestion, and obtain the real-time congestion information according to the real-time position; the prediction module 804 is used to obtain the real-time time, input the real-time time, the real-time position and the real-time congestion information into a pre-constructed traffic prediction model to obtain the traffic prediction information; the evaluation module 805 is used to input the decrypted information and the traffic prediction information into a pre-constructed traffic impact assessment model to obtain the traffic impact assessment information; the generation module 806 is used to construct a directed graph based on the vehicle information and the impact assessment information, and generate an optimized path based on the constructed directed graph in combination with the graph theory algorithm and the heuristic search strategy.

[0096] In this embodiment, the decryption and decompression module 801 includes: a first acquisition unit 8011, used to acquire vehicle information, the vehicle information includes driver information, vehicle model information and vehicle line information, the vehicle line information includes a transportation route, a starting point, multiple waypoints and a signing point; a second acquisition unit 8012, used to acquire vehicle sensor information corresponding to the transportation vehicle based on the license plate information, the vehicle sensor information includes vehicle-mounted GPS information, temperature and humidity information and acceleration information; a decryption and decompression unit 8013, used to acquire key information, decrypt the vehicle sensor information based on the key information and the decryption algorithm, and according to the compressed file type of the vehicle sensor information, use the corresponding compression software to decompress the vehicle sensor information to obtain the decrypted information; a backup unit 8014, used to back up the vehicle information, the vehicle sensor information and the decrypted information to a pre-selected backup storage node.

[0097] In this embodiment, the abnormal judgment module 802 includes: a first judgment unit 8021, which is used to confirm whether the transport vehicle has abnormal acceleration or abnormal deceleration based on acceleration information; a second judgment unit 8022, which is used to confirm the real-time position of the transport vehicle based on the on-board GPS information, and compare the real-time position with the vehicle lane information to determine whether there is abnormal deviation; a third judgment unit 8023, which is used to continuously obtain the on-board GPS information within a preset monitoring period to determine whether there is abnormal parking; an abnormal reporting unit 8024, which is used to generate a corresponding abnormal reporting instruction according to the abnormality type when there is abnormal acceleration, abnormal deceleration, abnormal deviation or abnormal parking.

[0098] In this embodiment, the acquisition module 803 includes: a fourth judgment unit 8031, which is used to determine whether there is a road congestion problem when abnormal deceleration and abnormal stopping problems occur; a confirmation unit 8032, which is used to confirm the real-time position of the transport vehicle according to the vehicle GPS information if there is a road congestion problem, and the real-time position is the real-time latitude and longitude coordinates; a third acquisition unit 8033, which is used to obtain real-time congestion information using a map service API according to the real-time position, and the real-time congestion information includes real-time road section information, congestion degree and estimated travel time.

[0099] In this embodiment, the prediction module 804 includes: a first conversion unit 8041, which is used to perform format conversion processing on the real-time time, the real-time location information and the real-time congestion information to obtain standard data; a fifth judgment unit 8042, which is used to judge whether the real-time time is a special time, and the special time includes morning rush hour, evening rush hour and holidays; a fourth acquisition unit 8043, which is used to obtain the impact weight corresponding to the real-time time when the real-time time is a special time; a prediction unit 8044, which is used to input the standard data and the impact weight into a traffic prediction model pre-built based on a CNN convolutional neural network to obtain traffic prediction information, and the traffic prediction information is the traffic conditions within a certain time period.

[0100] In this embodiment, the evaluation module 805 includes: a fifth acquisition unit 8051, which is used to use the meteorological service API to obtain weather change information corresponding to the real-time time and the real-time location; a second conversion unit 8052, which is used to perform format conversion processing on the temperature and humidity information included in the decrypted information to obtain standard temperature and humidity information; a first generation unit 8053, which is used to generate actual weather information corresponding to the real-time time and the real-time location according to the weather change information and the standard temperature and humidity information; an evaluation unit 8054, which is used to input the actual weather information and the traffic forecast information into a traffic impact assessment model pre-constructed based on a multivariate linear regression method to obtain traffic impact assessment information.

[0101] In this embodiment, the generation module 806 includes: a third conversion unit 8061, which is used to convert the vehicle model information, the vehicle line information and the evaluation information into nodes and edges of a directed graph, and define a weight function for the converted edges; a search unit 8062, which is used to use the Dijkstra algorithm to search for possible paths connecting the starting point and the sending and receiving points. During the search process, a greedy best priority search strategy is introduced, and the search process is optimized using a heuristic function; an output unit 8063, which is used to obtain an optimized path when the number of searches for possible paths reaches a preset number of iterations; a second generation unit 8064, which is used to generate a route change comparison diagram based on the optimized path and vehicle line information using a map API, and generate push information based on the route change comparison diagram and the driver information.

[0102] Based on the same idea as the method in the above embodiment, the device provided by the present application can implement the method in the above embodiment.

[0103] above Figure 8 The transport track monitoring device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The transport track monitoring device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0104] Fig. 9 1 is a schematic diagram of the structure of a transport track monitoring device provided by an embodiment of the present invention. The transport track monitoring device 900 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 910 (for example, one or more processors) and a memory 920, and one or more storage media 930 (for example, one or more mass storage devices) storing application programs 933 or data 932. Among them, the memory 920 and the storage medium 930 can be short-term storage or permanent storage. The program stored in the storage medium 930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the transport track monitoring device 900. Furthermore, the processor 910 can be configured to communicate with the storage medium 930, and execute a series of instruction operations in the storage medium 930 on the transport track monitoring device 900 to implement the steps of the transport track monitoring method provided by the above-mentioned method embodiments.

[0105] The transport track monitoring device 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input and output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Fig. 9 The structure of the transport track monitoring device shown does not constitute a limitation on the transport track monitoring device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0106] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the transport trajectory monitoring method.

[0107] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0108] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0109] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring a transport trajectory, characterized in that: include: Acquire vehicle information of the transport vehicle, acquire vehicle sensor information corresponding to the transport vehicle, decrypt and decompress the vehicle sensor information, and obtain decrypted information; Determine whether there is an abnormality based on the decrypted information and vehicle information, and if there is an abnormality, generate an abnormality reporting instruction; When the abnormal situation is road congestion, the real-time location of the transport vehicle is confirmed based on the decrypted information, and the real-time congestion information is obtained based on the real-time location; Acquire real-time time, and input the real-time time, the real-time location, and the real-time congestion information into a pre-built traffic prediction model to obtain traffic prediction information; Inputting the decrypted information and the traffic prediction information into a pre-built traffic impact assessment model to obtain traffic impact assessment information; A directed graph is constructed based on vehicle information and impact assessment information, and an optimized path is generated based on the constructed directed graph by combining graph theory algorithms and heuristic search strategies.

2. The method for monitoring the transport trajectory according to claim 1, characterized in that: The method of obtaining the vehicle information of the transport vehicle and the vehicle sensor information corresponding to the transport vehicle, and decrypting and decompressing the vehicle sensor information to obtain the decrypted information includes: Obtaining vehicle information, the vehicle information including driver information, vehicle model information and vehicle route information, the vehicle route information including a transportation route, a starting point, multiple passing points and a signing point; Based on the license plate information, obtain vehicle sensor information corresponding to the transport vehicle, wherein the vehicle sensor information includes vehicle-mounted GPS information, temperature and humidity information, and acceleration information; Acquire key information, decrypt the vehicle sensor information based on the key information and the decryption algorithm, and decompress the vehicle sensor information using corresponding compression software according to the compressed file type of the vehicle sensor information to obtain decrypted information; The vehicle information, the vehicle sensor information and the decrypted information are backed up to a pre-selected backup storage node.

3. The method for monitoring the transport trajectory according to claim 2, characterized in that: The determining whether there is an abnormality according to the decrypted information and the vehicle information, and if there is an abnormality, generating an abnormality reporting instruction, includes: Confirm whether the transport vehicle has abnormal acceleration or deceleration based on the acceleration information; Confirm the real-time position of the transport vehicle according to the vehicle-mounted GPS information, and compare the real-time position with the vehicle line information to determine whether there is abnormal deviation; During the preset monitoring time, the vehicle GPS information is continuously obtained to determine whether there is any abnormal stop; When there is abnormal acceleration, abnormal deceleration, abnormal deviation or abnormal stopping, a corresponding abnormal reporting instruction is generated according to the abnormal type.

4. The method for monitoring the transport trajectory according to claim 2, characterized in that: When the abnormal situation is road congestion, the real-time position of the transport vehicle is confirmed according to the decrypted information, and the real-time congestion information is obtained according to the real-time position, including: When abnormal deceleration and abnormal stopping occur, determine whether there is road congestion; If there is a road congestion problem, confirm the real-time location of the transport vehicle based on the vehicle GPS information, where the real-time location is the real-time latitude and longitude coordinates; According to the real-time position, a map service API is used to obtain real-time congestion information, wherein the real-time congestion information includes real-time road section information, congestion degree and estimated travel time.

5. The method for monitoring the transport trajectory according to claim 1, characterized in that: The acquiring of the real-time time, and inputting the real-time time, the real-time location, and the real-time congestion information into a pre-built traffic prediction model to obtain traffic prediction information, includes: Performing format conversion processing on the real-time time, the real-time location information, and the real-time congestion information to obtain standard data; Determine whether the real-time time is a special time, where the special time includes morning rush hour, evening rush hour and holidays; When the real-time time is a special time, obtaining an influence weight corresponding to the real-time time; The standard data and the influence weights are input into a traffic prediction model pre-built based on a CNN convolutional neural network to obtain traffic prediction information, where the traffic prediction information is the traffic conditions within a certain time period.

6. The method for monitoring the transport trajectory according to claim 2, characterized in that: The step of inputting the decrypted information and the traffic prediction information into a pre-built traffic impact assessment model to obtain traffic impact assessment information includes: Use the weather service API to obtain weather change information corresponding to real-time time and real-time location; Performing format conversion processing on the temperature and humidity information included in the decrypted information to obtain standard temperature and humidity information; Generating actual weather information corresponding to the real-time time and the real-time location according to the weather change information and the standard temperature and humidity information; The actual weather information and the traffic forecast information are input into a traffic impact assessment model pre-constructed based on a multiple linear regression method to obtain traffic impact assessment information.

7. The method for monitoring the transport trajectory according to claim 2, characterized in that: The method of constructing a directed graph based on vehicle information and impact assessment information, and generating an optimized path based on the constructed directed graph by combining a graph theory algorithm and a heuristic search strategy, includes: Convert the vehicle model information, the vehicle lane information, and the evaluation information into nodes and edges of a directed graph, and define a weight function for the converted edges; Use Dijkstra algorithm to search for possible paths connecting the starting point and the sending and receiving points. During the search process, introduce the greedy best-first search strategy and use the heuristic function to optimize the search process. When the number of searches for possible paths reaches the preset number of iterations, the optimized path is obtained; Based on the optimized path and vehicle lane information, a route change comparison diagram is generated using a map API, and push information is generated based on the route change comparison diagram and the driver information.

8. A transport track monitoring device, characterized in that: include: A decompression and decryption module is used to obtain vehicle information of the transport vehicle and vehicle sensor information corresponding to the transport vehicle, and decrypt and decompress the vehicle sensor information to obtain decrypted information; An abnormality judgment module is used to judge whether there is an abnormality based on the decrypted information and vehicle information, and if there is an abnormality, generate an abnormality reporting instruction; An acquisition module, used to confirm the real-time position of the transport vehicle according to the decrypted information when the abnormal situation is road congestion, and to acquire real-time congestion information according to the real-time position; A prediction module, used for obtaining real-time time, inputting the real-time time, the real-time location and the real-time congestion information into a pre-built traffic prediction model to obtain traffic prediction information; An evaluation module, used for inputting the decrypted information and the traffic prediction information into a pre-built traffic impact evaluation model to obtain traffic impact evaluation information; The generation module is used to construct a directed graph based on vehicle information and impact assessment information, and to generate an optimized path based on the constructed directed graph in combination with a graph theory algorithm and a heuristic search strategy.

9. A transport track monitoring device, characterized in that: The transport track monitoring device comprises: a memory and at least one processor, wherein instructions are stored in the memory; At least one of the processors calls the instructions in the memory to enable the transportation track monitoring device to execute each step of the transportation track monitoring method according to any one of claims 1 to 7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the transportation trajectory monitoring method as described in any one of claims 1 to 7 are implemented.

Images