Ship logistics alarm method and electronic equipment

Abstract

The invention relates to a shipping logistics alarm method and electronic equipment, relates to the technical field of shipping logistics, and can improve the reliability of a shipping logistics monitoring result. The method comprises the following steps: obtaining logistics chain data of shipping logistics in a current period, wherein the logistics chain data comprises at least one of video data, shipping travel data and wharf operation data; determining abnormal data of the shipping logistics according to the logistics chain data; and when the abnormal data meets a preset alarm condition, generating corresponding alarm information.

Description

Technical Field

[0001] The present disclosure relates to the technical field of shipping logistics, and in particular, to a shipping logistics alarm method and electronic equipment. Background Art

[0002] At present, some advanced information technology has been introduced into shipping logistics, but information technology can only realize simple data collection and information display. The monitoring of shipping logistics mainly relies on manual monitoring, which has low monitoring efficiency and is unable to detect potential risks in time, resulting in unreliable monitoring results of shipping logistics. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a shipping logistics alarm method and electronic equipment.

[0004] In order to achieve the above objectives, in a first aspect, the present disclosure provides a shipping logistics alarm method, the method comprising:

[0005] Acquire logistics chain data of shipping logistics in a current cycle, wherein the logistics chain data includes at least one of video data, ship operation data, and terminal operation data;

[0006] Determine the abnormal data of the shipping logistics according to the logistics chain data, the abnormal data include at least one of the operational abnormal data of the shipping logistics determined according to the video data, the itinerary abnormal data of the shipping logistics determined according to the shipping itinerary data, and the terminal scheduling abnormal data of the shipping logistics determined according to the terminal operation data, the operational abnormal data include the ship with operational abnormality in the shipping logistics, the start time of the operational abnormality, the abnormality type and the duration, the itinerary abnormal data include the yaw value, detention time and delay time of the ship with navigation abnormality in the shipping logistics, and the terminal scheduling abnormal data include the ship density, loading and unloading efficiency and throughput of the abnormal terminal in the shipping logistics;

[0007] When the abnormal data meets the preset alarm condition, corresponding alarm information is generated.

[0008] In a second aspect, the present disclosure provides a shipping logistics alarm device, the device comprising:

[0009] An acquisition module is configured to acquire logistics chain data of shipping logistics in a current cycle, wherein the logistics chain data includes at least one of video data, ship operation data, and terminal operation data;

[0010] a determination module configured to determine abnormal data of the shipping logistics according to the logistics chain data, wherein the abnormal data include at least one of abnormal operation data of the shipping logistics determined according to the video data, abnormal travel data of the shipping logistics determined according to the shipping travel data, and abnormal terminal scheduling data of the shipping logistics determined according to the terminal operation data, wherein the abnormal operation data include ships with abnormal operation in the shipping logistics, the start time of the abnormal operation, the type of abnormality, and the duration of the abnormal operation, the abnormal travel data include the yaw value, detention time, and delay time of ships with abnormal navigation in the shipping logistics, and the abnormal terminal scheduling data include the ship density, loading and unloading efficiency, and throughput of abnormal terminals in the shipping logistics;

[0011] The execution module is configured to generate corresponding alarm information when the abnormal data meets the preset alarm condition.

[0012] In a third aspect, the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which implements the method described in the first aspect when executed by a processor.

[0013] In a fourth aspect, the present disclosure provides an electronic device, including:

[0014] a memory having a computer program stored thereon;

[0015] A processor is used to execute the computer program in the memory to implement the method described in the first aspect.

[0016] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0017] Through the above technical solution, based on the video data, ship travel data and terminal data of shipping logistics in the current cycle, shipping logistics is intelligently monitored from multiple dimensions such as shipping logistics operation behavior, itinerary and terminal scheduling. The whole process does not involve manual processing and has high monitoring efficiency. It can timely discover potential risks of shipping logistics and generate alarm information, thereby improving the reliability of the monitoring results of shipping logistics.

[0018] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0020] Figure 1The figure is a flow chart of a shipping logistics alarm method according to an exemplary embodiment of the present disclosure.

[0021] Figure 2 is another flow chart of a shipping logistics alarm method according to an exemplary embodiment of the present disclosure.

[0022] Figure 3 It is another flow chart of a shipping logistics alarm method according to an exemplary embodiment of the present disclosure.

[0023] Figure 4 It is a block diagram of a shipping logistics alarm device according to an exemplary embodiment of the present disclosure.

[0024] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0026] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0027] It is worth noting that in recent years, with the rapid development of big data, cloud computing, the Internet of Things and artificial intelligence technologies, some advanced information technologies have begun to be introduced into fuel logistics chain management to realize shipping logistics alarms. For example, the business data of the operation site is collected through intelligent devices such as drones and cameras, the business data is processed and utilized using big data analysis technology, and intelligent algorithms are used to make intelligent recommendations for business decisions in complex decision-making scenarios, which has improved the intelligence level of fuel logistics chain management to a certain extent.

[0028] However, the inventors found that some advanced information technologies (such as drones, cameras, etc.) can only achieve simple data collection and display in fuel logistics chain management, and cannot achieve real-time and comprehensive monitoring of shipping logistics. At key nodes or complex scenarios in shipping logistics, it mainly relies on manual monitoring, which has low monitoring efficiency and cannot detect potential risks in time to issue alarms, resulting in unreliable monitoring results of shipping logistics.

[0029] In view of this, the present disclosure provides a shipping logistics alarm method and electronic equipment, which intelligently monitor shipping logistics from multiple dimensions, can timely discover potential risks of shipping logistics and generate alarm information, thereby improving the reliability of shipping logistics monitoring results.

[0030] Figure 1 FIG. 1 is a flow chart of a shipping logistics alarm method according to an exemplary embodiment of the present disclosure. The shipping logistics alarm method can be applied to smart devices such as laptops, personal terminals, tablet computers, smart wearable devices, etc. Figure 1 As shown, the shipping logistics alarm method may include the following steps:

[0031] In step S11, the logistics chain data of shipping logistics in the current cycle is obtained, and the logistics chain data includes at least one of video data, ship operation data and terminal operation data.

[0032] It is worth noting that the duration of each cycle can be preset according to the monitoring requirements of shipping logistics, and this disclosure does not limit this.

[0033] It is worth noting that the video data can cover the coal spilling status at the port of shipping logistics, the tarpaulin covering status of coal piles, the attire of port staff, the behavior of coal unloading grabbers, etc. Video data can be collected in real time by drone-mounted cameras or cameras installed in various scenes of shipping logistics (such as ships, docks, etc.) to collect video streams of various scenes of shipping logistics in the current cycle, such as port video streams, ship video streams, etc.

[0034] It is worth noting that the ship's itinerary data includes the ship's real-time coordinate information and expected coordinate information. The ship's real-time coordinate information can be obtained through positioning technology, including but not limited to the Global Positioning System (GPS), the Global Navigation Satellite System (GNSS) and base station positioning technology.

[0035] It is worth noting that the terminal operation data includes the arrival time of ships, departure time, loading and unloading volume, loading and unloading time, etc. The terminal operation data can be collected by radio frequency identification devices (RFID) installed at the terminal entrance and exit.

[0036] In step S12, abnormal data of the shipping logistics is determined according to the logistics chain data, and the abnormal data include at least one of the operational abnormality data of the shipping logistics determined according to the video data, the travel abnormality data of the shipping logistics determined according to the shipping itinerary data, and the terminal scheduling abnormality data of the shipping logistics determined according to the terminal operation data. The operational abnormality data include the ships with operational abnormalities in the shipping logistics, the start time of the operational abnormality, the type of abnormality and the duration of the operational abnormality. The travel abnormality data include the yaw value, detention time and delay time of the ships with navigation abnormalities in the shipping logistics. The terminal scheduling abnormality data include the ship density, loading and unloading efficiency and throughput of the abnormal terminals in the shipping logistics.

[0037] It is worth noting that the abnormal itinerary data of the shipping logistics determined based on the ship's itinerary data may include: the deviation value of the ship relative to the expected navigation plan can be obtained based on the real-time coordinate information and expected coordinate information of the ship; the DC duration can be obtained based on the stationary time of the implementation coordinate information of the ship; the difference between the predicted actual arrival time and the preset arrival time can be determined based on the real-time coordinate information of the ship to obtain the delay duration, wherein the predicted actual arrival time can be calculated based on the actual speed of the ship and the remaining voyage.

[0038] In step S13, when the abnormal data meets the preset alarm condition, corresponding alarm information is generated.

[0039] In the disclosed embodiment, the logistics chain data of shipping logistics in the current cycle includes at least one of video data, shipping itinerary data and terminal operation data, covering the main links of shipping logistics, ensuring the comprehensiveness and integrity of the data, thereby improving the response speed and decision-making efficiency of risk identification; the abnormal data determined according to the logistics chain data includes at least one of operation abnormality data, itinerary abnormality data and terminal scheduling data, and the risk of shipping logistics can be identified from multiple dimensions such as the operation behavior, itinerary and terminal scheduling of shipping logistics; when the abnormal data meets the preset alarm conditions, the corresponding alarm information is generated, ensuring the timely discovery and reporting of abnormal situations, which helps relevant personnel to quickly take measures to deal with them; and the entire process does not involve manual processing, reducing the error rate of manual intervention and risk identification, and can timely discover the potential risks of shipping logistics and generate alarm information, improve the reliability and accuracy of the monitoring results of shipping logistics, realize the intelligent monitoring and abnormality detection of shipping logistics, and improve the transparency and controllability of the logistics process.

[0040] In order to facilitate those skilled in the art to better understand the shipping logistics alarm method provided by the present disclosure, the steps of the shipping logistics method are described in detail below.

[0041] In a feasible implementation manner, before obtaining the logistics chain data of shipping logistics in the current cycle, the method may further include:

[0042] Dividing the shipping logistics into multiple areas by means of electronic fencing;

[0043] The multiple regions are divided into high-risk regions and ordinary regions, and the high-risk regions are controlled to refresh logistics chain data at a first frequency, and the ordinary regions are controlled to refresh logistics chain data at a second frequency, wherein the first frequency is greater than the second frequency.

[0044] It is worth noting that high-risk areas include but are not limited to sensitive areas, earthquake areas, navigation warning areas, pirate areas, marine protected areas and emission control areas (ECA), etc. Low-risk areas include but are not limited to docks, ports, anchorages and waterways, etc.

[0045] It is worth noting that multiple areas can be divided into high-risk areas and ordinary areas according to the high-risk areas of shipping logistics in the historical period; multiple areas can be divided into high-risk areas and ordinary areas according to the user's supervision requirements for each area of ​​shipping logistics; multiple areas can also be divided into high-risk areas and ordinary areas according to the warning information of shipping logistics in the previous period. This disclosure does not limit this.

[0046] In a feasible implementation manner, the multiple regions may be divided into high-risk regions and ordinary regions in the following manner:

[0047] Obtain the historical logistics chain data in each area, analyze and obtain the operation abnormality index, shipping abnormality index and scheduling abnormality index of each area, further calculate the logistics abnormality coefficient of each area, and set the default focus area based on the value of the logistics abnormality coefficient, that is, set the area with a high logistics abnormality coefficient value as a high-risk area.

[0048] In the disclosed embodiment, by controlling the refresh frequency of logistics chain data in high-risk areas and ordinary areas, key monitoring of high-risk areas and moderate monitoring of ordinary areas are achieved. The refresh frequency of logistics chain data in high-risk areas is greater than that in ordinary areas, so that high-risk areas can obtain more monitoring resources and attention, and reasonable allocation of security resources can be achieved; and through electronic fences and differentiated data refresh strategies, refined management of shipping logistics can be achieved, and on the basis of improving management efficiency, more accurate and comprehensive data support is provided to decision makers, helping decision makers to make more scientific and reasonable decisions.

[0049] In a feasible implementation manner, the abnormal operation data of the shipping logistics determined according to the video data includes:

[0050] Inputting the video data into a trained anomaly recognition model to obtain an abnormal image frame in the video data output by the anomaly recognition model, wherein the anomaly recognition model is used to identify target objects and irregular behaviors of personnel in the video data;

[0051] The ship where the abnormal operation occurs and the abnormal type are determined according to the object information and personnel behavior in the abnormal image frame, and the start time and duration of the abnormal operation are determined according to the timestamp of the abnormal image frame.

[0052] It is worth noting that the anomaly recognition models include but are not limited to deep learning models (YouOnlyLookOnce, YOLO), single shot multi-box detection models (SingleShotMultiBoxDetector, SSD), 3D convolutional neural network models (Convolutional Neural Networks 3D, C3D), temporal convolutional network models (TemporalConvolutional Networks, TCN) and image recognition models (Image Recognition Model, IRM). Among them, different deep learning models can be selected according to the degree of attention paid to different scenarios in shipping logistics. For example, in the scenarios of coal spilling at the port and coal piles covered with tarpaulins, YOLO or SSD is preferred to detect the position and category of objects in the video image, such as coal, tarpaulins, etc., and to determine whether coal is spilled or whether the coal pile is not covered or is not covered completely by tarpaulins; in the coal unloading scenario, C3D and TCN are preferred to be combined with the time dimension information of the video image to identify the operation behavior in the video image, such as whether the coal unloading grab is operated too fast, too slow, or has inaccurate position; in the scenario of port staff clothing recognition, IRM is preferred to recognize the clothing of people in the video image, such as whether the port staff are not wearing safety helmets or work clothes.

[0053] In the real-time mode of the present invention, a trained abnormal recognition model is used to quickly and accurately identify abnormal image frames in video data, avoiding the tedious and time-consuming manual screening, thereby improving the efficiency of abnormal behavior recognition and the accuracy of recognition results, and further improving the accuracy and reliability of operation abnormality data obtained based on the abnormal image frames output by the abnormal recognition model and the timestamps of the abnormal image frames.

[0054] In a feasible implementation manner, the anomaly recognition model is trained in the following manner:

[0055] Acquiring historical video data of the shipping logistics;

[0056] Splitting the historical video data into a plurality of initial single-frame images, and marking abnormal single-frame images among the plurality of initial single-frame images as abnormal, to obtain a plurality of intermediate single-frame images;

[0057] Dividing the plurality of intermediate single-frame images into a training set and a test set;

[0058] The model is trained through the training set, and the trained initial model is verified through the test set until the loss value of the initial model is a preset instantaneous value and the initial model reaches convergence, thereby obtaining an abnormality recognition model.

[0059] It is worth mentioning that the abnormal single-frame images among the multiple initial single-frame images include but are not limited to coal spillage, coal pile not covered by tarpaulin, improper coal unloading operation of coal unloading grab, and personnel stationed in the port not wearing safety helmets.

[0060] It is worth mentioning that the historical video data can be split into multiple initial single-frame images through the Open Source Computer Vision Library (OpenCV), and abnormal single-frame images with contents such as coal spillage, coal pile not covered by tarpaulin, irregular coal unloading operation of coal unloading grab, and personnel stationed in the port not wearing safety helmets in the multiple initial single-frame images are marked as abnormal, so as to obtain multiple intermediate single-frame images.

[0061] In the disclosed embodiments, historical video data is split into multiple initial single-frame images, which can efficiently utilize the time continuity and spatial information in the historical video data, thereby improving the accuracy and real-time performance of the output of the trained anomaly recognition model; abnormal single-frame images in the multiple initial single-frame images are marked as abnormal to obtain multiple intermediate single-frame images, which can improve the recognition ability of the trained anomaly recognition model and reduce false positives and negatives; the multiple intermediate single-frame images are divided into training sets and test sets for model training and verification, which can improve the generalization ability and recognition efficiency of the trained anomaly recognition model.

[0062] It is worth noting that in the embodiments of the present disclosure, the alarm information can be generated in two ways. Method 1: Generate alarm information based on the relationship between abnormal operation data, abnormal trip data, abnormal terminal scheduling data and their corresponding preset alarm conditions; Method 2: Calculate the logistics abnormality coefficient based on the abnormal operation data, abnormal trip data and abnormal terminal scheduling data, and generate alarm information based on the relationship between the logistics abnormality coefficient and its corresponding preset alarm conditions.

[0063] For method 1: generate alarm information based on the relationship between abnormal operation data, abnormal trip data and abnormal terminal scheduling data and their corresponding preset alarm conditions.

[0064] In a feasible implementation manner, when the abnormal data meets the preset alarm condition, corresponding alarm information is generated, including:

[0065] When at least one of the following conditions is met: the duration of the abnormal operation data is greater than the duration threshold, the deviation value of the abnormal trip data is greater than the deviation threshold, and the throughput in the abnormal terminal scheduling data is greater than the throughput threshold, corresponding alarm information is generated.

[0066] It is worth noting that the duration threshold, deviation threshold and throughput threshold can be preset according to the monitoring requirements of shipping logistics, and the present disclosure does not specifically limit this. In the embodiment of the present disclosure, the deviation threshold can be 20 meters.

[0067] It is worth noting that, when only the duration of the abnormal operation data is greater than the duration threshold, an alarm message is generated to prompt that the operation specification of shipping logistics needs to be optimized; when only the deviation value of the abnormal trip data is greater than the deviation threshold, an alarm message is generated to prompt that the shipping trip needs to be optimized; when only the throughput in the abnormal terminal scheduling data is greater than the throughput threshold, an alarm message is generated to prompt that the terminal scheduling needs to be optimized. Accordingly, when any two of the above three conditions are met at the same time, an alarm message is generated to prompt that the corresponding two shipping logistics need to be optimized.

[0068] For example, Figure 2 As shown, the shipping logistics alarm method provided by the present disclosure may include the following steps:

[0069] In step S11, the logistics chain data of shipping logistics in the current cycle is obtained, and the logistics chain data includes at least one of video data, ship operation data and terminal operation data.

[0070] In step S12, abnormal data of the shipping logistics is determined according to the logistics chain data, and the abnormal data include at least one of the operational abnormality data of the shipping logistics determined according to the video data, the travel abnormality data of the shipping logistics determined according to the shipping itinerary data, and the terminal scheduling abnormality data of the shipping logistics determined according to the terminal operation data. The operational abnormality data include the ships with operational abnormalities in the shipping logistics, the start time of the operational abnormality, the type of abnormality and the duration of the operational abnormality. The travel abnormality data include the yaw value, detention time and delay time of the ships with navigation abnormalities in the shipping logistics. The terminal scheduling abnormality data include the ship density, loading and unloading efficiency and throughput of the abnormal terminals in the shipping logistics.

[0071] In step S1311, when at least one of the following conditions is met: the duration of the abnormal operation data is greater than the duration threshold, the deviation value of the abnormal trip data is greater than the deviation threshold, and the throughput in the abnormal terminal scheduling data is greater than the throughput threshold, a corresponding alarm message is generated.

[0072] In the disclosed embodiment, by directly comparing abnormal data with the corresponding preset alarm conditions, alarm information can be quickly generated. The whole process is intuitive and easy to understand, which is convenient for operators to quickly understand and respond. In addition, the preset alarm conditions can be adjusted and optimized according to actual monitoring needs, and can flexibly adapt to different logistics scenarios and terminal scheduling needs.

[0073] For method 2: Calculate the logistics abnormality coefficient based on the operation abnormality data, trip abnormality data and terminal scheduling abnormality data, and generate alarm information based on the relationship between the logistics abnormality coefficient and its corresponding preset alarm condition.

[0074] In a feasible implementation manner, when the abnormal data meets the preset alarm condition, corresponding alarm information is generated, including:

[0075] determining an operation abnormality index according to the operation abnormality data;

[0076] Determining a shipping abnormality index according to the abnormal trip data;

[0077] Determining a scheduling abnormality index according to the terminal scheduling abnormality data;

[0078] Normalizing the operation abnormality index, the shipping abnormality index, and the scheduling abnormality index respectively, and calculating a logistics abnormality coefficient according to the normalized operation abnormality index, the normalized shipping abnormality index, and the normalized shipping abnormality index;

[0079] When the logistics anomaly coefficient is greater than the coefficient threshold, a corresponding alarm message is generated.

[0080] It is worth noting that the coefficient threshold can be preset according to the monitoring requirements of shipping logistics, and the present disclosure does not limit this.

[0081] For example, the operation abnormality index CY is determined according to the operation abnormality data, the shipping abnormality index HY is determined according to the trip abnormality data, and the scheduling abnormality index MH is determined according to the terminal scheduling abnormality data; CY, HY and MH are normalized respectively, and the normalized CY, HY and MH are substituted into the following calculation formula to obtain the logistics abnormality coefficient LAC:

[0082]

[0083] The operation quality of shipping logistics is quantified by the logistics anomaly coefficient. When the logistics anomaly coefficient is greater than the coefficient threshold, an alarm message is generated to prompt the need to optimize the operating specifications, ship operation schedule and terminal scheduling of shipping logistics.

[0084] For example, Figure 3 As shown, the shipping logistics alarm method provided by the present disclosure may include the following steps:

[0085] In step S11, the logistics chain data of shipping logistics in the current cycle is obtained, and the logistics chain data includes at least one of video data, ship operation data and terminal operation data.

[0086] In step S12, abnormal data of the shipping logistics is determined according to the logistics chain data, and the abnormal data include at least one of the operational abnormality data of the shipping logistics determined according to the video data, the travel abnormality data of the shipping logistics determined according to the shipping itinerary data, and the terminal scheduling abnormality data of the shipping logistics determined according to the terminal operation data. The operational abnormality data include the ships with operational abnormalities in the shipping logistics, the start time of the operational abnormality, the type of abnormality and the duration of the operational abnormality. The travel abnormality data include the yaw value, detention time and delay time of the ships with navigation abnormalities in the shipping logistics. The terminal scheduling abnormality data include the ship density, loading and unloading efficiency and throughput of the abnormal terminals in the shipping logistics.

[0087] In step S1321, an operation abnormality index is determined according to the operation abnormality data.

[0088] In step S1322, a shipping abnormality index is determined based on the abnormal trip data.

[0089] In step S1323, a scheduling abnormality index is determined according to the terminal scheduling abnormality data.

[0090] In step S1324, the operation abnormality index, the shipping abnormality index and the scheduling abnormality index are normalized respectively, and the logistics abnormality coefficient is calculated according to the normalized operation abnormality index, the normalized shipping abnormality index and the normalized shipping abnormality index.

[0091] In step S1325, when the logistics abnormality coefficient is greater than the coefficient threshold, a corresponding alarm message is generated.

[0092] In the disclosed embodiment, the impact of various abnormal data is comprehensively considered by calculating the logistics abnormality coefficient, which can more comprehensively reflect the overall situation of logistics operation and terminal scheduling. By setting a reasonable logistics abnormality coefficient threshold, the severity of abnormal conditions in shipping logistics can be more accurately judged, thereby generating more accurate alarm information, which can provide operators with longer response time and decision-making space.

[0093] In a feasible implementation manner, the method for obtaining the operation abnormality index may include:

[0094] determining a fuel weight involved in the operation abnormality according to the operation abnormality data;

[0095] The operation abnormality index is obtained according to the fuel weight, the duration in the operation abnormality data and the following calculation formula:

[0096]

[0097] Among them, CY represents the abnormal operation index, n represents the number of abnormal operations in shipping logistics, i represents the sequence number of the current abnormal operation, ct i Indicates the duration of the current abnormal operation, yq i The preset weight coefficient that characterizes the current abnormal operation, ym i The fuel weight representing the current abnormal operation, Ls represents the loss value of the abnormality recognition model used to output the operation abnormality data according to the video data.

[0098] Among them, the preset weight coefficient can be preset manually, and this disclosure does not limit this.

[0099] In a feasible implementation manner, the method for obtaining the shipping anomaly index may include:

[0100] Performing multivariate linear regression processing according to the meteorological factors of the shipping logistics and the ship load to obtain the yaw value influence coefficient, the detention time influence coefficient and the delay time influence coefficient, wherein the meteorological factors include at least one of wind speed, wind direction, wave height, visibility and precipitation;

[0101] The shipping abnormality index is obtained according to the yaw value influence coefficient, the detention time influence coefficient, the delay time influence coefficient, the yaw value, the detention time, the delay time and the following calculation formula:

[0102]

[0103] Among them, HY represents the shipping anomaly index, m represents the time point when the navigation anomaly occurs in the shipping logistics, j represents the sequence number of the current navigation anomaly, and hp j The yaw value that represents the current navigation abnormality, αhp Characterizes the influence coefficient of the yaw value of the current navigation abnormality, hz j Characterizes the detention time of the current navigation anomaly, α hz Characterizes the detention time impact coefficient of the current navigation anomaly, ht j Characterizes the delay time of the current navigation anomaly, α ht The delay time influence coefficient representing the current navigation abnormality, f1, f2, f3 represent the weight factors of each item respectively, and f1+f2+f3=1.

[0104] It is worth noting that the ship load and meteorological factors can be used as independent variables, and the yaw value influence coefficient, detention time influence coefficient or delay time influence coefficient can be used as dependent variables. The correlation between meteorological factors and abnormal shipping information can be analyzed by statistical methods or machine learning models. According to the results of the correlation analysis, the degree of influence of meteorological factors on the yaw value, detention time or delay time can be quantified as a specific influence coefficient, and then the accuracy and reliability of the quantification results can be evaluated by cross-validation or other verification methods. Specifically, the correlation analysis between meteorological factors and abnormal shipping information can be achieved through regression analysis, correlation analysis or decision trees.

[0105] For example, when the meteorological factors are qx1, qx1, ..., qx q , a total of q as an example, through regression analysis, the influence of meteorological factors on the yaw value is quantified as the yaw value influence coefficient, which can include the following steps:

[0106] The heading deviation value y hp is the dependent variable, the meteorological factors (qx1, qx1, …, qx q ) and ship load fz as independent variables, and the following multiple linear regression model is constructed:

[0107] y hp =β0+β1·qx1+β2·qx2+…+β q ·qx q +β x ·fz+ε,

[0108] Among them, y hp Characterize the theoretical yaw values, β0, β1, ..., β q , β x represents the preset regression coefficient, and ε represents the correction constant.

[0109] y hp Substitute into the following calculation formula to obtain the yaw value influence coefficient α hp :

[0110]

[0111] Among them, hp represents the actual yaw value.

[0112] Correspondingly, the retention time influence coefficient α is obtained by the above calculation method: hz And the delay time influence coefficient α ht .

[0113] In a feasible implementation manner, the method for obtaining the scheduling anomaly index may include:

[0114] Divide the abnormal terminal scheduling data into multiple time intervals according to a preset time period, and determine the ship density fluctuation coefficient, loading and unloading efficiency fluctuation coefficient and throughput fluctuation coefficient of the terminal with abnormal scheduling in the shipping logistics according to the ship density, loading and unloading efficiency and throughput in each time interval;

[0115] According to the fluctuation coefficient of the ship density, the fluctuation coefficient of the loading and unloading efficiency, the fluctuation coefficient of the throughput and the following calculation formula, the scheduling abnormality index is obtained:

[0116]

[0117] Among them, MH represents the scheduling abnormality index, dm represents the fluctuation coefficient of the ship density of the terminal with scheduling abnormalities in the shipping logistics, dx represents the fluctuation coefficient of the loading and unloading efficiency of the terminal with scheduling abnormalities in the shipping logistics, dt represents the throughput fluctuation coefficient of the terminal with scheduling abnormalities in the shipping logistics, w1, w2 and w3 represent the weight coefficients of each item, and w1+w2+w3=1.

[0118] In the embodiment of the present disclosure, the operation abnormality index CY, the shipping abnormality index HY and the scheduling abnormality index MH are calculated respectively to realize the refined evaluation of the operation quality of the fuel logistics chain; the logistics abnormality coefficient LAC obtained according to the operation abnormality index CY, the shipping abnormality index HY and the scheduling abnormality index MH can intuitively reflect the overall operation status of the fuel logistics chain; when the logistics abnormality coefficient exceeds the coefficient threshold, an alarm message is generated to prompt the need to optimize the operating specifications, ship operation schedule and terminal scheduling of shipping logistics, which provides intelligent decision-making support for managers, helps managers to discover problems in time and take targeted measures, thereby effectively reducing potential safety risks.

[0119] It is worth noting that the entire process of the shipping logistics alarm method can be visualized. For example, the video data, ship operation data, terminal operation data and alarm information of the current cycle of shipping logistics are displayed, so that managers can dynamically monitor the real-time position of the ship, the dress code of the port staff, the coal unloading situation at the port and the covering status of the coal pile tarpaulin. And managers can also allocate shipping logistics in time according to the visualization content. For example, based on the predicted density of incoming ships and loading and unloading volume of the port, human and material resources are dispatched; according to the alarm information, the working hours and task allocation of port staff are reasonably arranged to ensure sufficient manpower support during peak hours; according to the loading and unloading needs, loading and unloading equipment and transportation vehicle resources are deployed in advance to ensure the efficient loading and unloading operations; according to the predicted density of incoming ships and loading and unloading volume, storage space is reasonably planned to avoid cargo accumulation and congestion.

[0120] Based on the same inventive concept, the present disclosure also provides a shipping logistics alarm device, such as Figure 4 As shown, the shipping logistics alarm device includes an acquisition module 401, a determination module 402 and an execution module 403.

[0121] The acquisition module 401 is configured to acquire logistics chain data of shipping logistics in the current cycle, wherein the logistics chain data includes at least one of video data, shipping itinerary data, and terminal operation data;

[0122] The determination module 402 is configured to determine the abnormal data of the shipping logistics according to the logistics chain data, wherein the abnormal data includes at least one of the operational abnormality data of the shipping logistics determined according to the video data, the itinerary abnormality data of the shipping logistics determined according to the shipping itinerary data, and the terminal scheduling abnormality data of the shipping logistics determined according to the terminal operation data, wherein the operational abnormality data includes the ship with the operational abnormality in the shipping logistics, the start time of the operational abnormality, the abnormality type, and the duration, the itinerary abnormality data includes the yaw value, detention time, and delay time of the ship with the navigation abnormality in the shipping logistics, and the terminal scheduling abnormality data includes the ship density, loading and unloading efficiency, and throughput of the abnormal terminal in the shipping logistics;

[0123] The execution module 403 is configured to generate corresponding alarm information when the abnormal data meets the preset alarm condition.

[0124] In the disclosed embodiment, the logistics chain data of shipping logistics in the current cycle includes at least one of video data, shipping itinerary data and terminal operation data, covering the main links of shipping logistics, ensuring the comprehensiveness and integrity of the data, thereby improving the response speed and decision-making efficiency of risk identification; the abnormal data determined according to the logistics chain data includes at least one of operation abnormality data, itinerary abnormality data and terminal scheduling data, and the risk of shipping logistics can be identified from multiple dimensions such as the operation behavior, itinerary and terminal scheduling of shipping logistics; when the abnormal data meets the preset alarm conditions, the corresponding alarm information is generated, ensuring the timely discovery and reporting of abnormal situations, which helps relevant personnel to quickly take measures to deal with them; and the entire process does not involve manual processing, reducing the error rate of manual intervention and risk identification, and can timely discover the potential risks of shipping logistics and generate alarm information, improve the reliability and accuracy of the monitoring results of shipping logistics, realize the intelligent monitoring and abnormality detection of shipping logistics, and improve the transparency and controllability of the logistics process.

[0125] Optionally, the execution module 403 is configured to generate corresponding alarm information when at least one of the following conditions is met: the duration of the abnormal operation data is greater than a duration threshold, the deviation value of the abnormal trip data is greater than a deviation threshold, and the throughput in the abnormal terminal scheduling data is greater than a throughput threshold.

[0126] Optionally, the execution module 403 is configured to determine an operation abnormality index according to the operation abnormality data;

[0127] Determining a shipping abnormality index according to the abnormal trip data;

[0128] Determining a scheduling abnormality index according to the terminal scheduling abnormality data;

[0129] Normalizing the operation abnormality index, the shipping abnormality index, and the scheduling abnormality index respectively, and calculating a logistics abnormality coefficient according to the normalized operation abnormality index, the normalized shipping abnormality index, and the normalized shipping abnormality index;

[0130] When the logistics anomaly coefficient is greater than the coefficient threshold, a corresponding alarm message is generated.

[0131] Optionally, the execution module 403 is configured to determine the fuel weight involved in the operation abnormality according to the operation abnormality data;

[0132] The operation abnormality index is obtained according to the fuel weight, the duration in the operation abnormality data and the following calculation formula:

[0133]

[0134] Among them, CY represents the abnormal operation index, n represents the number of abnormal operations in shipping logistics, i represents the sequence number of the current abnormal operation, ct i Indicates the duration of the current abnormal operation, yq i The preset weight coefficient that characterizes the current abnormal operation, ym i The fuel weight representing the current abnormal operation, Ls represents the loss value of the abnormality recognition model used to output the operation abnormality data according to the video data.

[0135] Optionally, the execution module 403 is configured to perform multivariate linear regression processing according to the meteorological factors of the shipping logistics and the ship load to obtain the yaw value influence coefficient, the detention time influence coefficient and the delay time influence coefficient, wherein the meteorological factors include at least one of wind speed, wind direction, wave height, visibility and precipitation;

[0136] The shipping abnormality index is obtained according to the yaw value influence coefficient, the detention time influence coefficient, the delay time influence coefficient, the yaw value, the detention time, the delay time and the following calculation formula:

[0137]

[0138] Among them, HY represents the shipping anomaly index, m represents the time point when the navigation anomaly occurs in the shipping logistics, j represents the sequence number of the current navigation anomaly, and hp j The yaw value that represents the current navigation abnormality, α hp Characterizes the influence coefficient of the yaw value of the current navigation abnormality, hz j Characterizes the detention time of the current navigation anomaly, α hz Characterizes the detention time impact coefficient of the current navigation anomaly, ht j Characterizes the delay time of the current navigation anomaly, α ht The delay time influence coefficient representing the current navigation abnormality, f1, f2, f3 represent the weight factors of each item respectively, and f1+f2+f3=1.

[0139] Optionally, the execution module 403 is configured to divide the abnormal terminal scheduling data into multiple time intervals according to a preset time period, and determine the ship density fluctuation coefficient, loading and unloading efficiency fluctuation coefficient and throughput fluctuation coefficient of the terminal with scheduling abnormality in the shipping logistics according to the ship density, the loading and unloading efficiency and the throughput in each time interval;

[0140] According to the fluctuation coefficient of the ship density, the fluctuation coefficient of the loading and unloading efficiency, the fluctuation coefficient of the throughput and the following calculation formula, the scheduling abnormality index is obtained:

[0141]

[0142] Among them, MH represents the scheduling abnormality index, dm represents the fluctuation coefficient of the ship density of the terminal with scheduling abnormalities in the shipping logistics, dx represents the fluctuation coefficient of the loading and unloading efficiency of the terminal with scheduling abnormalities in the shipping logistics, dt represents the throughput fluctuation coefficient of the terminal with scheduling abnormalities in the shipping logistics, w1, w2 and w3 represent the weight coefficients of each item, and w1+w2+w3=1.

[0143] Optionally, the determination module 402 is configured to input the video data into a trained anomaly recognition model to obtain an abnormal image frame in the video data output by the anomaly recognition model, wherein the anomaly recognition model is used to identify target objects and irregular behaviors of personnel in the video data;

[0144] The ship where the abnormal operation occurs and the abnormal type are determined according to the object information and personnel behavior in the abnormal image frame, and the start time and duration of the abnormal operation are determined according to the timestamp of the abnormal image frame.

[0145] Optionally, the shipping logistics alarm device further comprises a training module, the training module being configured to obtain historical video data of the shipping logistics;

[0146] Splitting the historical video data into a plurality of initial single-frame images, and marking abnormal single-frame images among the plurality of initial single-frame images as abnormal, to obtain a plurality of intermediate single-frame images;

[0147] Dividing the plurality of intermediate single-frame images into a training set and a test set;

[0148] The model is trained through the training set, and the trained initial model is verified through the test set until the loss value of the initial model is a preset instantaneous value and the initial model reaches convergence, thereby obtaining an abnormality recognition model.

[0149] Optionally, the acquisition module 401 is configured to divide the shipping logistics into a plurality of areas by means of electronic fences before acquiring the logistics chain data of the shipping logistics in the current cycle;

[0150] The multiple regions are divided into high-risk regions and ordinary regions, and the high-risk regions are controlled to refresh logistics chain data at a first frequency, and the ordinary regions are controlled to refresh logistics chain data at a second frequency, wherein the first frequency is greater than the second frequency.

[0151] Regarding the shipping logistics alarm device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0152] Based on the same inventive concept, the present disclosure also provides an electronic device, including:

[0153] a memory having a computer program stored thereon;

[0154] A processor is used to execute the computer program in the memory to implement the above-mentioned shipping logistics alarm method.

[0155] In the disclosed embodiment, the logistics chain data of shipping logistics in the current cycle includes at least one of video data, shipping itinerary data and terminal operation data, covering the main links of shipping logistics, ensuring the comprehensiveness and integrity of the data, thereby improving the response speed and decision-making efficiency of risk identification; the abnormal data determined according to the logistics chain data includes at least one of operation abnormality data, itinerary abnormality data and terminal scheduling data, and the risk of shipping logistics can be identified from multiple dimensions such as the operation behavior, itinerary and terminal scheduling of shipping logistics; when the abnormal data meets the preset alarm conditions, the corresponding alarm information is generated, ensuring the timely discovery and reporting of abnormal situations, which helps relevant personnel to quickly take measures to deal with them; and the entire process does not involve manual processing, reducing the error rate of manual intervention and risk identification, and can timely discover the potential risks of shipping logistics and generate alarm information, improve the reliability and accuracy of the monitoring results of shipping logistics, realize the intelligent monitoring and abnormality detection of shipping logistics, and improve the transparency and controllability of the logistics process.

[0156] Figure 5 FIG. 5 is a block diagram of an electronic device 500 according to an exemplary embodiment. Figure 5 As shown, the electronic device 500 may include: a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0157] The processor 501 is used to control the overall operation of the electronic device 500 to complete all or part of the steps in the above-mentioned shipping logistics alarm method. The memory 502 is used to store various types of data to support the operation of the electronic device 500, and these data may include, for example, instructions for any application or method used to operate on the electronic device 500, and application-related data, such as video data, ship operation data, terminal operation data, operation abnormality data, itinerary abnormality data, and terminal scheduling abnormality data. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 502 or sent via the communication component 505. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 504 provides an interface between the processor 501 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 505 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0158] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned shipping logistics alarm method.

[0159] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned shipping logistics alarm method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 502 including program instructions, and the above-mentioned program instructions can be executed by the processor 501 of the electronic device 500 to complete the above-mentioned shipping logistics alarm method.

[0160] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned shipping logistics alarm method when executed by the programmable device.

[0161] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0162] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0163] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A shipping logistics alarm method, characterized in that: The method comprises: Acquire logistics chain data of shipping logistics in a current cycle, wherein the logistics chain data includes at least one of video data, ship operation data, and terminal operation data; Determine the abnormal data of the shipping logistics according to the logistics chain data, the abnormal data include at least one of the operational abnormal data of the shipping logistics determined according to the video data, the itinerary abnormal data of the shipping logistics determined according to the shipping itinerary data, and the terminal scheduling abnormal data of the shipping logistics determined according to the terminal operation data, the operational abnormal data include the ship with operational abnormality in the shipping logistics, the start time of the operational abnormality, the abnormality type and the duration, the itinerary abnormal data include the yaw value, detention time and delay time of the ship with navigation abnormality in the shipping logistics, and the terminal scheduling abnormal data include the ship density, loading and unloading efficiency and throughput of the abnormal terminal in the shipping logistics; When the abnormal data meets the preset alarm condition, corresponding alarm information is generated.

2. The shipping logistics alarm method according to claim 1, characterized in that: When the abnormal data meets the preset alarm conditions, corresponding alarm information is generated, including: When at least one of the following conditions is met: the duration of the abnormal operation data is greater than the duration threshold, the deviation value of the abnormal trip data is greater than the deviation threshold, and the throughput in the abnormal terminal scheduling data is greater than the throughput threshold, corresponding alarm information is generated.

3. The shipping logistics alarm method according to claim 1, characterized in that: When the abnormal data meets the preset alarm conditions, corresponding alarm information is generated, including: determining an operation abnormality index according to the operation abnormality data; Determining a shipping abnormality index according to the abnormal trip data; Determining a scheduling abnormality index according to the terminal scheduling abnormality data; Normalizing the operation abnormality index, the shipping abnormality index, and the scheduling abnormality index respectively, and calculating a logistics abnormality coefficient according to the normalized operation abnormality index, the normalized shipping abnormality index, and the normalized shipping abnormality index; When the logistics anomaly coefficient is greater than the coefficient threshold, a corresponding alarm message is generated.

4. The shipping logistics alarm method according to claim 3, characterized in that: The method for obtaining the operation abnormality index includes: determining a fuel weight involved in the operation abnormality according to the operation abnormality data; The operation abnormality index is obtained according to the fuel weight, the duration in the operation abnormality data and the following calculation formula: Among them, CY represents the abnormal operation index, n represents the number of abnormal operations in shipping logistics, i represents the sequence number of the current abnormal operation, ct i Indicates the duration of the current abnormal operation, yq i The preset weight coefficient that characterizes the current abnormal operation, ym i The fuel weight representing the current abnormal operation, Ls represents the loss value of the abnormality recognition model used to output the operation abnormality data according to the video data.

5. The shipping logistics alarm method according to claim 3, characterized in that: The method for obtaining the shipping abnormality index includes: Performing multivariate linear regression processing according to the meteorological factors of the shipping logistics and the ship load to obtain the yaw value influence coefficient, the detention time influence coefficient and the delay time influence coefficient, wherein the meteorological factors include at least one of wind speed, wind direction, wave height, visibility and precipitation; The shipping abnormality index is obtained according to the yaw value influence coefficient, the detention time influence coefficient, the delay time influence coefficient, the yaw value, the detention time, the delay time and the following calculation formula: Among them, HY represents the shipping anomaly index, m represents the time point when the navigation anomaly occurs in the shipping logistics, j represents the sequence number of the current navigation anomaly, and hp j The yaw value that represents the current navigation abnormality, α hp Characterizes the influence coefficient of the yaw value of the current navigation abnormality, hz j Characterizes the detention time of the current navigation anomaly, α hz Characterizes the detention time impact coefficient of the current navigation anomaly, ht j Characterizes the delay time of the current navigation anomaly, α ht The delay duration influence coefficient representing the current navigation abnormality, f1, f2, f3 represent the weight factors of each item respectively, and f1+f2+f3=1.

6. The shipping logistics alarm method according to claim 3, characterized in that: The method for obtaining the scheduling anomaly index includes: Divide the abnormal terminal scheduling data into multiple time intervals according to a preset time period, and determine the ship density fluctuation coefficient, loading and unloading efficiency fluctuation coefficient and throughput fluctuation coefficient of the terminal with abnormal scheduling in the shipping logistics according to the ship density, loading and unloading efficiency and throughput in each time interval; According to the fluctuation coefficient of the ship density, the fluctuation coefficient of the loading and unloading efficiency, the fluctuation coefficient of the throughput and the following calculation formula, the scheduling abnormality index is obtained: Among them, MH represents the scheduling abnormality index, dm represents the fluctuation coefficient of the ship density of the terminal with scheduling abnormalities in the shipping logistics, dx represents the fluctuation coefficient of the loading and unloading efficiency of the terminal with scheduling abnormalities in the shipping logistics, dt represents the throughput fluctuation coefficient of the terminal with scheduling abnormalities in the shipping logistics, w1, w2 and w3 represent the weight coefficients of each item, and w1+w2+w3=1.

7. The shipping logistics alarm method according to any one of claims 1 to 6, characterized in that: The abnormal operation data of the shipping logistics determined according to the video data includes: Inputting the video data into a trained anomaly recognition model to obtain an abnormal image frame in the video data output by the anomaly recognition model, wherein the anomaly recognition model is used to identify target objects and irregular behaviors of personnel in the video data; The ship where the abnormal operation occurs and the abnormal type are determined according to the object information and personnel behavior in the abnormal image frame, and the start time and duration of the abnormal operation are determined according to the timestamp of the abnormal image frame.

8. The shipping logistics alarm method according to claim 7, characterized in that: The anomaly recognition model is trained in the following way: Acquiring historical video data of the shipping logistics; Splitting the historical video data into a plurality of initial single-frame images, and marking abnormal single-frame images among the plurality of initial single-frame images as abnormal, to obtain a plurality of intermediate single-frame images; Dividing the plurality of intermediate single-frame images into a training set and a test set; The model is trained through the training set, and the trained initial model is verified through the test set until the loss value of the initial model is a preset instantaneous value and the initial model reaches convergence, thereby obtaining an abnormality recognition model.

9. The shipping logistics alarm method according to any one of claims 1 to 6, characterized in that: Before obtaining the logistics chain data of shipping logistics in the current cycle, the method further includes: Dividing the shipping logistics into multiple areas by means of electronic fencing; The multiple regions are divided into high-risk regions and ordinary regions, and the high-risk regions are controlled to refresh logistics chain data at a first frequency, and the ordinary regions are controlled to refresh logistics chain data at a second frequency, wherein the first frequency is greater than the second frequency.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the method according to any one of claims 1 to 9.

Images