Port cargo circulation dynamic carbon footprint generation method and device

Abstract

The invention discloses a port cargo circulation dynamic carbon footprint generation method and device. The method comprises the steps that image data, positioning data and environment variables generated in the circulation process of port goods are collected, time and space alignment is carried out, and a multi-modal fusion dynamic data set is formed; detecting activity level information of the logistics equipment from the dynamic data set by adopting artificial intelligence; through a multi-factor dynamic emission model, carbon emission of the port cargoes in different logistics links is calculated in combination with a dynamic adjustment coefficient and activity level information, and the dynamic adjustment coefficient is used for correcting power emission and fuel emission; a dynamic correlation model of time, space and logistics equipment is constructed by combining image data and positioning data, and then the whole-flow dynamic carbon footprint of the port cargo in the circulation process is generated by utilizing the carbon emission of the port cargo in different logistics links; the technical problem that in the prior art, carbon emission calculation is low in accuracy in the carbon footprint generation process is at least solved.

Description

Technical Field

[0001] The present application relates to the technical field of logistics management and carbon emission calculation, and in particular to a method and device for generating a dynamic carbon footprint of port cargo circulation. Background Art

[0002] This section is intended to provide a background or context to what is stated in the claims or specification, and no admission is made that what is described herein is prior art by inclusion in this section.

[0003] The concept of "carbon footprint" originates from "ecological footprint", which mainly uses carbon dioxide emission equivalent (CO2equivalent, referred to as: CO2eq) to represent the total greenhouse gas emissions emitted during human production and consumption activities. Compared with single carbon dioxide emissions, carbon footprint uses life cycle assessment method to evaluate the greenhouse gas emissions directly or indirectly generated by the research object during its life cycle. For the same object, the difficulty and scope of carbon footprint calculation are greater than carbon emissions, and its calculation results include information on carbon emissions.

[0004] As an important node in the global logistics chain, carbon emission management in the cargo flow process of ports has become the key to achieving green development goals. However, existing technologies have the following prominent problems in calculating carbon emissions in different links and generating carbon footprints throughout the entire process: 1) Insufficient correlation between activity level and emission factor: Current carbon emission calculation methods usually use fixed emission factors, which fail to dynamically reflect the impact of equipment operating status, load changes and environmental variables, resulting in large calculation errors; 2) The calculation method of carbon emissions at each stage lacks dynamism and accuracy: Existing technologies mostly use a single fuel emission factor or power emission factor for calculation, which fails to comprehensively consider the dynamic impact of multiple factors such as power output, fuel consumption, load changes and environmental variables; 3) The generation of the entire carbon footprint process lacks dynamic correlation: Current methods mostly rely on the simple accumulation of carbon emissions in each link, and fail to generate a continuous carbon footprint from the perspective of dynamic correlation of time, space and equipment, making it difficult to accurately describe the complexity of port logistics; 4) Low utilization of multimodal data: Port operations generate a large amount of video data, GPS trajectory data, and environmental variable data. Existing technologies fail to fully utilize the complementarity of these data, resulting in insufficient accuracy in calculating equipment activity levels and carbon emissions.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiment of the present application provides a method and device for generating a dynamic carbon footprint of port cargo circulation, so as to at least solve the technical problem of low accuracy of carbon emission calculation in the carbon footprint generation process of the prior art. This solution accurately obtains the activity level of equipment in the process of port cargo circulation through complementary analysis of video images and positioning trajectories (such as GPS trajectories), and at the same time combines innovative multi-factor fusion dynamic emission calculation methods, dynamic adjustment coefficients and full-process dynamic modeling technology to generate a dynamic carbon footprint of port cargo circulation, providing scientific decision-making support for green port construction.

[0007] According to one aspect of an embodiment of the present application, a method for generating a dynamic carbon footprint of port cargo circulation is provided, including: collecting image data, positioning data and environmental variables generated by port cargo during circulation, and aligning the image data, positioning data and environmental variables in time and space to form a multi-modal fused dynamic data set; using artificial intelligence to detect activity level information of logistics equipment from the dynamic data set, the activity level information includes equipment type, operation status, operation duration and load change of the logistics equipment; using a multi-factor dynamic emission model, combining a dynamic adjustment coefficient and activity level information to calculate the carbon emissions of port cargo in different logistics links, and the dynamic adjustment coefficient is used to correct power emissions and fuel emissions; combining image data and positioning data to construct a dynamic correlation model of time, space and logistics equipment, and then using the carbon emissions of port cargo in different logistics links to generate a full-process dynamic carbon footprint of port cargo in the circulation process.

[0008] Optionally, image data, positioning data and environmental variables generated by port cargo during circulation are collected, and the image data, positioning data and environmental variables are aligned in time and space to form a multimodal fused dynamic data set, including: collecting image data of logistics equipment through fixed cameras and drones, obtaining the operation trajectory, operation speed and location information of the logistics equipment through the positioning module on the logistics equipment, and collecting the temperature, humidity and wind speed of the port operating environment through temperature and humidity sensors and anemometers. The positioning data includes the operation trajectory, operation speed and location information, and the environmental variables include temperature, humidity and wind speed; based on timestamp synchronization technology and spatial alignment technology, the image data, positioning data and environmental variables are aligned in time and space to form a multimodal fused dynamic data set.

[0009] Optionally, artificial intelligence is used to detect the activity level information of logistics equipment from dynamic data sets, including: using deep learning models to detect targets on image data, identify equipment categories, operating status, and load changes; using time series models LSTM to track and predict dynamic changes in operating status; calculating the operating time of logistics equipment in the operating state through image data, and estimating the dynamic load of logistics equipment in combination with load changes Lcurrent =L base +ΔL , L base is the load before the change, ΔL It is the load change; combined with the positioning data, the operation status and operation duration are verified.

[0010] Optionally, the operating status includes loading and unloading status, idle status and transport status, and the operating status is verified in combination with the positioning data, including: when the operating speed determined according to the positioning data is greater than 0, verifying that the logistics equipment is in a transport state; when the operating speed determined according to the positioning data is equal to 0, verifying that the logistics equipment is in a loading and unloading state or an idle state.

[0011] Optionally, the carbon emissions of port cargo in different logistics links are calculated by combining the dynamic adjustment coefficient and activity level information through a multi-factor dynamic emission model, including: calculating the carbon emissions of logistics equipment in different operating states based on the multi-factor dynamic emission model CF :

[0012] CF Indicates the carbon emissions at each stage, T statei Indicates that logistics equipment is i The duration of each job in each job state, P i Represents the output power of logistics equipment, EF poweri represents the power emission factor, Fi Indicates fuel consumption, EF fueli represents the fuel emission factor, α(Ei,Li) Indicates the dynamic adjustment coefficient. α(Ei,Li) The calculation formula is:

[0013] ΔT=T−T ref , indicating the current temperature T With reference temperature T ref The difference between ΔH=H−H ref , indicating the current humidity H With reference humidity H ref The difference between W Indicates the current wind speed. ΔL=L−L ref , indicating the current load L The difference between the reference load and k1, k2, k3, k4 Indicates the weight of the dynamic adjustment coefficient.

[0014] Optionally, a dynamic correlation model of time, space and logistics equipment is constructed by combining image data and positioning data, and then the carbon emissions of port goods in different logistics links are used to generate the dynamic carbon footprint of the whole process of port goods in the circulation process, including: based on time modeling, capturing the dynamic conversion time points of logistics equipment between loading and unloading state, idling state and transportation state, and the operation duration of each operation state; based on space modeling, combining positioning data and regional division algorithm, capturing the dynamic path of logistics equipment in different spatial locations; based on operation state modeling, using deep learning model and positioning data to analyze the state switching and load change of logistics equipment; using the following formula to generate the whole process carbon emission footprint:

[0015] CF total represents the carbon emissions of the entire process, CF i (t) Indicates i Logistics equipment at a time t The instantaneous carbon emissions, T Represents the total time of the logistics process.

[0016] Optionally, in the process of building a dynamic correlation model of time, space and logistics equipment by combining image data and positioning data, and then using the carbon emissions of port cargo in different logistics links to generate a full-process dynamic carbon footprint of port cargo in the circulation process, the method also includes: combining image data and positioning data to verify the dynamic path, operating status and load changes of quasi-logistics equipment, and outputting a complete carbon footprint report.

[0017] According to another aspect of the embodiment of the present application, a device for generating a dynamic carbon footprint of port cargo circulation is also provided, including: a collection unit, used to collect image data, positioning data and environmental variables generated by port cargo during the circulation process, and to align the image data, positioning data and environmental variables in time and space to form a multi-modal fused dynamic data set; a detection unit, used to use artificial intelligence to detect the activity level information of logistics equipment from the dynamic data set, the activity level information includes the equipment type, operation status, operation duration and load change of the logistics equipment; a calculation unit, used to calculate the carbon emissions of port cargo in different logistics links through a multi-factor dynamic emission model combined with a dynamic adjustment coefficient and activity level information, and the dynamic adjustment coefficient is used to correct power emissions and fuel emissions; a generation unit, used to construct a dynamic correlation model of time, space and logistics equipment in combination with image data and positioning data, and then use the carbon emissions of port cargo in different logistics links to generate a full-process dynamic carbon footprint of the port cargo in the circulation process.

[0018] According to another aspect of an embodiment of the present application, a computer-readable storage medium is further provided, the storage medium including a stored program, and the above method is executed when the program is run.

[0019] According to another aspect of an embodiment of the present application, an electronic device is further provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above method through the computer program.

[0020] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any one of the embodiments of the above method.

[0021] In the embodiment of the present application, the image data, positioning data and environmental variables generated by the port cargo in the circulation process are collected, and the image data, positioning data and environmental variables are aligned in time and space to form a dynamic data set of multimodal fusion; artificial intelligence is used to detect the activity level information of the logistics equipment from the dynamic data set, and the activity level information includes the equipment type, operation status, operation duration and load change of the logistics equipment; through the multi-factor dynamic emission model, the dynamic adjustment coefficient and the activity level information are combined to calculate the carbon emissions of the port cargo in different logistics links, and the dynamic adjustment coefficient is used to correct the power emission and fuel emission; the image data and positioning data are combined to build a dynamic association model of time, space and logistics equipment, and then the carbon emissions of the port cargo in different logistics links are used to generate the dynamic carbon footprint of the whole process of the port cargo in the circulation process. The technical problem of low accuracy of carbon emission calculation in the carbon footprint generation process of the prior art can be solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a flow chart of an optional method for generating a dynamic carbon footprint of port cargo circulation according to an embodiment of the present application; Figure 2 is a schematic diagram of an optional solution for generating a dynamic carbon footprint of port cargo circulation according to an embodiment of the present application; Figure 3 is a schematic diagram of an optional device for generating a dynamic carbon footprint of port cargo circulation according to an embodiment of the present application; Figure 4 It is a structural block diagram of a terminal according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations 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.

[0025] According to one aspect of the embodiments of the present application, a method embodiment of a method for generating a dynamic carbon footprint of port cargo circulation is provided. A method for generating a dynamic carbon footprint of port cargo circulation based on multimodal data fusion and intelligent optimization algorithm is provided, which optimizes emission factors in real time and generates a dynamic carbon footprint of port cargo circulation through complementary analysis of video images and GPS trajectories, combined with a multi-factor fusion dynamic emission model and a dynamic adjustment coefficient, and with the support of full-process dynamic modeling technology.

[0026] The present invention constructs a dynamic carbon footprint generation system for port cargo circulation based on multimodal data fusion and intelligent optimization algorithm, which mainly includes the following core modules: 1) Multimodal data acquisition and fusion module: collects video image data and GPS data, and combines environmental variable data to obtain equipment activity level through complementary analysis; 2) Activity level calculation module: based on multimodal data, dynamically calculates the activity time and load changes of equipment under different states; 3) Innovative link-by-link carbon emission calculation module: through a multi-factor dynamic emission model, combined with a dynamic adjustment coefficient, accurately calculates the carbon emissions of different logistics links; 4) Full-process carbon footprint dynamic modeling module: based on the combination of video and GPS data, constructs a dynamic association model of time, space and equipment to generate a full-process dynamic carbon footprint of the port cargo circulation process.

[0027] Figure 1 is a flow chart of an optional method for generating a dynamic carbon footprint of port cargo circulation according to an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps: Step S102, collect image data, positioning data and environmental variables generated during the circulation of port cargo, and align the image data, positioning data and environmental variables in time and space to form a multi-modal fused dynamic data set.

[0028] Step S104, using artificial intelligence to detect the activity level information of the logistics equipment from the dynamic data set, the activity level information includes the equipment type, operation status (or equipment status), operation duration (or operation duration, operating time, etc.) and load change of the logistics equipment.

[0029] Step S106, using a multi-factor dynamic emission model, combined with dynamic adjustment coefficients and activity level information, calculates the carbon emissions of port cargo in different logistics links. The dynamic adjustment coefficients are used to correct power emissions and fuel emissions.

[0030] Step S108, combining the image data and positioning data to build a dynamic correlation model of time, space and logistics equipment, and then using the carbon emissions of port goods in different logistics links to generate a full-process dynamic carbon footprint of port goods in the circulation process.

[0031] The above solution has the following advantages, which can solve the technical problem of low accuracy of carbon emission calculation in the process of carbon footprint generation: Accurate calculation of activity levels: Using the multimodal fusion method of video images and GPS data, the device status is dynamically identified to obtain the activity time and load changes under different states; Innovative calculation method of carbon emissions at different stages: a dynamic emission model based on multi-factor fusion is proposed, combined with dynamic adjustment coefficients, comprehensively considering power, fuel emission factors, load, environmental variables and dynamic characteristics of equipment, to accurately calculate carbon emissions at different logistics stages; Full-process dynamic modeling: Based on the combination of video and GPS data, a dynamic correlation model between time, space and equipment is established to generate a complete dynamic carbon footprint of the port cargo flow process; Multimodal data fusion technology: Capture equipment operation status and load changes through video images, and combine GPS data to calibrate activities. As an optional embodiment, the following is combined with specific implementation methods, Figure 2 Detailed description of the technical solution of this application: Step 1: Multimodal data collection and fusion (collecting image data, positioning data and environmental variables generated by port cargo during circulation, and aligning the image data, positioning data and environmental variables in time and space to form a multimodal fused dynamic data set) 1) Data collection source: Video image data: collect equipment operation videos through fixed cameras and drones to identify equipment categories, operating status, and load changes; GPS data: collect equipment operation tracks and location information through the GPS module on the equipment, which is used to calibrate video analysis results; Environmental variable data: collect real-time environmental conditions through temperature and humidity sensors and anemometers, including variables such as temperature, humidity, and wind speed.

[0032] 2) Data fusion method: Complementary analysis of video and GPS uses video images to identify equipment status (such as loading and unloading, idling, and transportation), and calibrates the equipment's path and activity area through GPS data to achieve complementary analysis of status and trajectory; time and space alignment synchronizes video, GPS, and environmental variable data with timestamps and spatial coordinates to form a multi-modal fused dynamic data set.

[0033] Step 2: Activity level calculation (using artificial intelligence to detect the activity level information of the logistics equipment from the dynamic data set. The activity level information may be referred to as the activity level, including the equipment type, operation status, operation duration and load change of the logistics equipment) 1) Activity level definition Running time: the time the equipment is active in different states (such as loading and unloading, idling, and transportation).

[0034] Load changes: Capture changes in equipment load status (such as loading weight) through video image data, and analyze the equipment's transportation distance in combination with GPS trajectory.

[0035] 2) Activity level calculation method 2.1) Multimodal Data Input for State Recognition State recognition relies on video data and auxiliary sensor data of the device (such as GPS, IMU, etc.), and achieves high-precision recognition of device status through multimodal input.

[0036] Input data includes: Video data: Equipment operation videos are collected through fixed cameras or drones to detect the operating status of the equipment (such as transportation, loading and unloading, idling, etc.); GPS data: Provides equipment location information and speed to assist in verifying status identification results; Load change data: Captures equipment load changes through video or sensors to reflect the equipment's operating intensity.

[0037] 2.2) Design and optimization of deep learning models In this invention, deep learning models (YOLOv5 and LSTM) are used to process video data to complete state recognition and time calculation. The following are the specific design and optimization details of the model: (1) YOLOv5: Real-time Object Detection Equipment and load detection for complex port scene videos: Detection targets: equipment type (such as crane, transport vehicle), equipment operating status (such as loading and unloading, transportation, idling), cargo load (such as container, bulk cargo volume); Output results: Through the bounding box output of YOLOv5, the spatial position of the equipment or goods is located in real time, and its category and status are marked.

[0038] Model optimization: Data enhancement: Perform data enhancement (such as rotation, scaling, noise addition, etc.) on port scene video data to improve the model's adaptability to complex scenes; Custom data sets: Based on port-specific tasks (such as loading and unloading, transportation status detection), train models to improve detection accuracy; Multi-scale detection: Detect objects of different sizes (such as large equipment and small cargo) to ensure the robustness of the model in complex scenarios.

[0039] (2) LSTM: Time Series Analysis and State Tracking Applicable to dynamic change analysis of port equipment status: Input sequence: The equipment status sequence (such as loading and unloading, idling, and transportation) output by YOLOv5 is input into the LSTM model to analyze the changing trend of the equipment status in the time dimension; Output state: predict the current state of the device and its duration, for example: State current : Current status (such as transportation, loading and unloading), T state =t stop −t start : Status duration.

[0040] Model optimization: State smoothing: LSTM is used to filter short-term fluctuations to avoid misjudgment of state (such as misidentifying a short pause as idling); State transition analysis: Based on the historical state sequence, predict the next possible state (such as transitioning to transportation after loading and unloading is completed).

[0041] (3) Multimodal fusion: combining video and sensor data To improve the accuracy of state recognition, the deep learning model fuses video data with GPS or other sensor data: Time synchronization: align the video frame with the timestamp of GPS data to ensure the consistency of data in the time dimension; Status verification: The device status of video recognition is verified through the speed and trajectory characteristics of GPS. For example, when the video detection is "transportation status", it is verified by combining the GPS speed Vgps>0; when the video detection is "idling status", it is verified by combining the GPS zero speed Vgps=0.

[0042] 2.3) State recognition and time calculation process The entire state recognition and time calculation process is as follows: (1) Target detection and state classification Video input: pre-processing of port operation videos (such as denoising and resolution adjustment); Object detection: Use YOLOv5 to detect equipment, goods and their operating status; Status classification: Perform a preliminary classification of the device status and output the following results: State i : The current status of the equipment (such as transport, loading and unloading, idling); Box i : The detected position and bounding box of the device.

[0043] (2) Time series analysis and state tracking Sequence input: The state sequence output by YOLOv5 is used as the input of LSTM.

[0044] State tracking: Analyze the state changes of the device through LSTM and predict its current state and duration.

[0045] Time calculation: Combined with the video frame timestamp, calculate the duration of each state: T state =t stop −t start in, t start and t stop The start and end times of the state, respectively.

[0046] (3) Dynamic calculation of load changes Load detection: Detect the presence and quantity changes of cargo through YOLOv5, for example: detect the change in the number of containers (such as the number of containers decreasing from 1 to 0 during loading and unloading); detect the change in the volume of bulk cargo (such as the volume of cargo increasing during loading); Dynamic load adjustment: Dynamically update the load L of the device according to the detection results: L current =L base +ΔL, in, L base is the initial load, ΔL is the load variation.

[0047] (4) Status and time verification Verification of status identification and time calculation via GPS data: Status verification: Combined with GPS speed V gps Verify the status of video detection, for example: if V gps >0 , verify that the device is in "shipping" condition, if V gps =0 , verify that the equipment is in "loading and unloading" or "idling" state; Path verification: Combined with GPS tracks, determine whether the equipment is in the correct operating area.

[0048] 2.4) Output Through the above calculation process, the activity level data of port equipment is generated, including: Device status sequence: {State1,State2,…,Staten}; The time corresponding to each state T state and load L; State duration: the time interval between each state T state ; Load change sequence: Dynamic changes in equipment load L current .

[0049] Step 3: Innovative calculation of carbon emissions at different stages (using a multi-factor dynamic emission model, combined with a dynamic adjustment coefficient and the activity level information to calculate the carbon emissions of port cargo at different logistics stages. The dynamic adjustment coefficient is used to correct power emissions and fuel emissions) 1) Dynamic adjustment coefficient α(Ei,Li) Dynamic adjustment coefficient α(Ei,Li) It is a dynamic parameter used to correct the power emission factor and fuel emission factor, taking into account the following two types of influencing factors: Environmental variables Ei: include temperature (T), humidity (H) and wind speed (W), which affect the combustion efficiency and emission characteristics of the equipment.

[0050] Load status Li: Dynamically captures the load and operating status of the equipment (such as no load, full load, idling, etc.) through video images and GPS data, reflecting the impact of the actual operating load of the equipment on emissions.

[0051] The calculation formula of the dynamic adjustment coefficient is:

[0052] ΔT=T−T ref : The difference between the current temperature and the reference temperature; ΔH=H−H ref : The difference between the current humidity and the reference humidity; W: current wind speed; ΔL=L−L ref : The difference between the current load and the reference load; k1, k2, k3, k4: weights of environmental and load variables, determined by historical data and model training.

[0053] The correction formula for the emission factor through dynamic adjustment coefficient is: Power emission factor correction:

[0054] Fuel emission factor correction:

[0055] 2) Dynamic adjustment method combining video and GPS To ensure dynamic adjustment coefficient α(Ei,Li) In order to improve the calculation accuracy, the present invention uses multimodal analysis technology that combines video and GPS data to dynamically capture the equipment operation status and load changes, and integrates them with real-time data of environmental variables to form a complete dynamic adjustment framework.

[0056] 2.1) The role of video data The video data is trained using deep learning models (such as YOLOv5 and LSTM) to achieve the following functions: Equipment operation status recognition: Use video images to recognize the current operation status of the equipment (such as loading and unloading, idling, and transportation) to provide status input for activity level calculations. Use video to monitor the boom movement frequency of the crane to determine whether it is in the loading and unloading state. Load estimation: Estimate the current load L by analyzing the cargo volume, equipment loading action and other information through video. Detect the quantity or volume of cargo on the transport vehicle through video and dynamically update the load value; Runtime capture: Accurately calculate the activity time in different states based on the start and stop times of devices in the video.

[0057] 2.2) The role of GPS data GPS data can be analyzed and calibrated through trajectory to achieve the following functions: Path calibration and activity area analysis: Calibrate the equipment status and activity area identified by the video through the displacement and speed changes between GPS track points. When the equipment is moving at a low speed and is located in the yard area, it can assist in verifying that it is in a loading and unloading state; Dynamic state change capture: Combine speed and acceleration (calculated by GPS trajectory) to assist in determining the dynamic state of the device (such as transport, idling). Determine whether the device is in transport or unloaded driving state by the speed change of the trajectory point; Temporal and spatial alignment: Align the timestamp of GPS data with the video data to ensure the synchronization of multimodal data in time and space.

[0058] 2.3) Complementary analysis of video and GPS The combination of video and GPS data enables high-precision dynamic capture of equipment operating status and load changes: Status verification: The device status (such as loading and unloading, idling) of video recognition is calibrated through GPS trajectory data to eliminate misjudgment that may be caused by a single data source. When the video recognition device is in the loading and unloading state, GPS is combined to confirm that the device is indeed in the yard area, which can avoid misjudgment caused by video viewing angle occlusion; Dynamic capture of load changes: The load estimated by the video is further verified by the distance and speed characteristics of the GPS track, forming a multi-dimensional dynamic input of the load state; Improved activity level calculation accuracy: Through complementary analysis of video and GPS data, the activity time and load changes of equipment in different states are accurately calculated, providing high-quality input data for dynamic adjustment coefficients.

[0059] Multi-factor fusion dynamic emission model The dynamic emission model proposed in the present invention comprehensively considers the following factors: equipment operating status, output power, fuel consumption, load and environmental variables, and accurately calculates carbon emissions in each link.

[0060] Emission calculation formula:

[0061] CF: Carbon emissions by stage; T statei ： No. i Activity time of the session; Pi: Equipment output power; EF poweri ： Power emission factor; Fi: Fuel consumption; EF fueli ： Fuel emission factors; α(Ei,Li): Dynamic adjustment coefficient.

[0062] Step 4: Dynamic modeling of the carbon footprint of the entire process (combining image data and positioning data to build a dynamic correlation model of time, space and logistics equipment, and then using the carbon emissions of port goods in different logistics links to generate a dynamic carbon footprint of the entire process of port goods in the circulation process) 1) Dynamic association model between time, space and equipment The time, space and equipment dynamic correlation model designed by the present invention takes multimodal data as the core input, establishes the correlation between the equipment operation status in time, space and between devices through dynamic analysis combining video and GPS, and constructs a dynamic carbon emission path.

[0063] 1.1) Model Input Video data: Real-time capture of equipment operating status and load changes for status identification and activity level calculation; GPS track data: provides the equipment's running path, location information, and speed changes for calibration status, path analysis, and activity area division; Environmental variable data: including parameters such as temperature, humidity, wind speed, etc., which are used to correct emission factors and dynamically adjust carbon emission calculation results.

[0064] 1.2) Model structure The model is divided into three core parts: time modeling, space modeling and equipment status modeling.

[0065] (1) Temporal modeling Temporal modeling captures the operation patterns and carbon emission changes of equipment in different periods through time series analysis of equipment status changes; Time series analysis method: Use recurrent neural network (RNN) or long short-term memory network (LSTM) to model the time series data of the equipment and identify the dynamic transitions between the equipment's running, idling, loading and unloading, and transportation states; Equipment state time association: Extract the key state change points Tstart and Tstop of the equipment through the timestamp of the video data, and combine them with the GPS speed change points to establish the activity time of each state: T state =T stop −T start (2) Spatial modeling Spatial modeling uses the GPS trajectory information of the equipment and combines it with the work area division to capture the dynamic path of the equipment in different spatial locations.

[0066] Trajectory analysis and activity area division: Based on GPS data, the key operation areas of the equipment (such as yards, loading and unloading areas, and transportation channels) are identified through trajectory clustering algorithms (such as DBSCAN), and the trajectories are divided into different operation scenarios; Path optimization and calibration: Calibrate the moving path of the equipment through GPS tracks to ensure the continuity and accuracy of the path, and verify whether the equipment is actually in a certain operating area by combining video data; Spatial association modeling formula: The spatial path modeling formula of the equipment is:

[0067] in, S path is the total path length, xi,yi are the coordinates of the trajectory points.

[0068] (3) Equipment status modeling Equipment status modeling uses video data combined with deep learning algorithms (such as YOLOv5) to detect the equipment's operating status (loading and unloading, idling, transportation) and load changes in real time, and calibrates state switching in combination with GPS data.

[0069] Multi-device interaction modeling: Using graph neural networks (GNN) to build dynamic interaction relationships between device states, such as the impact of collaborative operations between loading and unloading equipment and transport vehicles on carbon emissions; State recognition and update formula: State recognition dynamically updates the device state by analyzing the device's motion features Fvideo through video and combining them with GPS speed changes Vgps:

[0070] 1.3) Carbon emission path generation Combining the dynamic relationship between time, space and equipment status, the full-process carbon emission path of the equipment is generated, and the formula is:

[0071] CFtotal: Carbon footprint of the entire process; CFi(t): No. i The instantaneous carbon emissions of a device at time t; T： The total time of the logistics process.

[0072] 2) Dynamic footprint generation combining video and GPS 2.1) The role of video data Equipment status recognition: Use deep learning models (such as YOLOv5) to analyze video images in real time to identify the equipment’s operating status (loading, unloading, idling, transportation) and load changes; Activity time capture: Through device action recognition in the video, the key activity time points of the device are captured and combined with the timestamp to generate time series data; Load change estimation: Dynamically estimate the load of the equipment by analyzing the equipment's operating actions (such as loading and unloading) through video.

[0073] 2.2) The role of GPS data Path calibration and activity area division: Calibrate the equipment path through GPS trajectory data and identify key operation areas (such as yards and loading and unloading areas); Speed ​​and status verification: Combine speed and acceleration changes from GPS data to verify the device status (such as transport or idling) identified by the video; Temporal and spatial alignment: Align the timestamp of GPS data with the video data to ensure the synchronization of multimodal data.

[0074] 2.3) Complementary analysis of video and GPS Status verification: The device status of video recognition is calibrated through GPS track to ensure the accuracy of status recognition. For example, when the video recognition device is in the loading and unloading state, the GPS track is combined to confirm whether the device is in the loading and unloading area; Capture of load changes: The load amount (such as cargo weight) estimated by the video is further verified by the transportation path of the GPS track to dynamically adjust the load status; Activity level calculation optimization: By combining video and GPS data, the activity time and path of the device in different states can be accurately calculated, providing high-quality input for carbon emission calculation.

[0075] The present application also provides a preferred embodiment, which further details the technical solution of the present application in combination with specific scenarios: Background: A port handles 1 million TEUs of containerized cargo every year. The port management needs to evaluate the dynamic carbon emissions of a single batch of cargo (1 TEU, 20-foot container) during loading and unloading, transportation, and yard operations. Since port operations involve a variety of equipment and complex scenarios, traditional static carbon emission calculation methods cannot capture dynamic changes (such as equipment status switching, load changes, environmental impact, etc.), so the solution of the present invention is used to perform dynamic carbon footprint calculation of the entire process.

[0076] Case data, the logistics process of handling a single batch of goods involves the links and data shown in Table 1 below: Table 1

[0077] Environment variables: Temperature T = 35°C, reference temperature T ref =25℃; Humidity H=80%, reference humidity H ref =50%; Wind speed W = 5 m / s; Carbon emission factor: Fuel emission factor EF fuel =2.68 kgCO2; Power emission factor EF power =0.85 kgCO2 / kWh.

[0078] Implementation steps Step 1: Multimodal data collection and fusion Data collection: Video data: Use fixed cameras and drones to collect equipment operation videos and identify equipment status (loading, unloading, transportation, idling).

[0079] GPS data: Records the path, speed and location of transport trucks and forklifts.

[0080] Environmental variable data: collect real-time temperature, humidity and wind speed at the port.

[0081] Data Fusion: Use the time and space alignment algorithm of the present invention to synchronize multimodal data: Video frame timestamps are aligned with GPS trajectory data; According to the spatial coordinates of the equipment, the equipment status is mapped to specific scenes (such as yards, transportation channels, docks, etc.).

[0082] Multimodal data fusion results: Crane status: loading and unloading cargo, the state switching time is 0.5 seconds; Transport truck status: the transport route is 5 km, and the speed range is 0-30 km / h; Forklift status: transporting goods in the yard, load change is +2 m³.

[0083] Step 2: Activity Level Calculation The YOLOv5+LSTM model of the present invention is used to dynamically calculate the device activity level.

[0084] Device status identification: The YOLOv5 model recognizes device status through video images: Crane status: loading and unloading; Transport truck status: transport, idling; Forklift status: transporting goods.

[0085] Model accuracy: The state recognition accuracy reaches 96%.

[0086] Time Series Analysis: Use the LSTM model to perform time series prediction on device status changes and calculate the device activity time: Crane loading and unloading time: 15 minutes; Transport time by transport truck: 30 minutes; Forklift operation time: 20 minutes; Crane and truck idling time: 25 minutes.

[0087] Load change calculation: During crane loading and unloading, the load change is ΔL=+1 (loading 1 container).

[0088] During the forklift handling process, the load change is ΔL=+2m³ (handling bulk cargo).

[0089] Based on the GPS data, the transport truck load was verified to change from full to empty (ΔL = −1).

[0090] Step 3: Multi-factor dynamic carbon emission calculation Dynamic adjustment coefficient calculation: According to the dynamic adjustment coefficient formula:

[0091] Weight setting: k1=0.01, k2=0.005, k3=0.02, k4=0.05.

[0092] Crane (loading and unloading): α=1+(0.01×10)+(0.005×30)+(0.02×5)+(0.05×1)=1.45.

[0093] Transport Truck (Transport): α=1+(0.01×10)+(0.005×30)+(0.02×5)+(0.05×(−1))=1.35.

[0094] Forklift (handling): α=1+(0.01×10)+(0.005×30)+(0.02⋅5)+(0.05×2)=1.55.

[0095] Carbon emissions calculation: According to the formula:

[0096] Crane (loading and unloading): CF=15 / 60×(0+5×2.68)×1.45=2.91 kgCO 2 Transport Truck (Transport): CF=30 / 60×(150×0.85+0)×1.35=51.53kgCO 2 Forklift (handling): CF=20 / 60 × (0+3 × 2.68) × 1.55=4.16 kgCO 2 Idle speed (crane / truck): CF=25 / 60 × (0+2 × 2.68) × 1.35=3.02 kgCO 2 Step 4: Dynamic carbon footprint modeling of the entire process Full process carbon emission path generation: Summarize the carbon emissions of each link: CF total =2.91+51.53+4.16+3.02=61.62kgCO 2 Spatial distribution: Yard area (loading and unloading + yard operation): total 7.07 kgCO 2; Transportation route (truck transportation): total 51.53 kgCO 2.

[0097] Analysis of high emission links: The highest proportion of carbon emissions comes from transport trucks: 51.5361.62≈83.6%.

[0098] Results and optimization suggestions Total carbon emissions: The dynamic carbon footprint of a single shipment is 61.62 kgCO2.

[0099] Optimization suggestions: Route optimization: Adjust the routes of transport trucks to reduce route length.

[0100] Equipment replacement: Gradually introduce electric or hybrid delivery trucks.

[0101] Improved operating efficiency: Reduce equipment idling time and optimize operating processes through intelligent scheduling.

[0102] The multimodal fusion algorithm, dynamic carbon emission model and full-process modeling method adopted in this plan not only quantified the carbon emissions of the entire process, but also identified the high-emission links and proposed optimization directions, providing a scientific basis for the construction of green ports.

[0103] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0105] According to another aspect of the embodiments of the present application, a device for generating a dynamic carbon footprint of port cargo circulation for implementing the above-mentioned method for generating a dynamic carbon footprint of port cargo circulation is also provided. Figure 3 is a schematic diagram of an optional device for generating a dynamic carbon footprint of port cargo circulation according to an embodiment of the present application, such as Figure 3 As shown, the device may include: The acquisition unit 31 is used to collect image data, positioning data and environmental variables generated by port cargo during circulation, and to perform time and space alignment on the image data, the positioning data and the environmental variables to form a multi-modal fused dynamic data set.

[0106] The detection unit 33 is used to detect the activity level information of the logistics equipment from the dynamic data set using artificial intelligence, wherein the activity level information includes the equipment type, operation status, operation duration and load change of the logistics equipment.

[0107] The calculation unit 35 is used to calculate the carbon emissions of port cargo in different logistics links through a multi-factor dynamic emission model, combined with a dynamic adjustment coefficient and the activity level information, wherein the dynamic adjustment coefficient is used to correct power emissions and fuel emissions.

[0108] The generation unit 37 is used to combine the image data and the positioning data to build a dynamic correlation model of time, space and logistics equipment, and then use the carbon emissions of port goods in different logistics links to generate a full-process dynamic carbon footprint of the port goods in the circulation process.

[0109] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware.

[0110] Optionally, the acquisition unit can also be used to: collect image data of logistics equipment through fixed cameras and drones, obtain the operation trajectory, operation speed and location information of the logistics equipment through the positioning module on the logistics equipment, and collect the temperature, humidity and wind speed of the port operating environment through temperature and humidity sensors and anemometers, the positioning data includes the operation trajectory, the operation speed and the location information, and the environmental variables include temperature, humidity and wind speed; based on timestamp synchronization technology and spatial alignment technology, the image data, the positioning data and the environmental variables are aligned in time and space to form a multi-modal fused dynamic data set.

[0111] Optionally, the detection unit can also be used to: use a deep learning model to perform target detection on the image data to identify the equipment category, operating status and load changes; use a time series model LSTM to track and predict the dynamic changes of the operating status; calculate the operating time of the logistics equipment in the operating state through the image data, and estimate the dynamic load of the logistics equipment in combination with the load changes L current =L base +ΔL ,in, L base is the load before the change, ΔL is the load change; and the operation status and the operation duration are verified in combination with the positioning data.

[0112] Optionally, the detection unit can also be used to: when the running speed determined according to the positioning data is greater than 0, verify that the logistics equipment is in a transportation state; when the running speed determined according to the positioning data is equal to 0, verify that the logistics equipment is in a loading and unloading state or an idling state.

[0113] Optionally, the calculation unit can also be used to: calculate the carbon emissions of logistics equipment under different operating conditions based on the multi-factor dynamic emission model CF :

[0114] in, CF Indicates the carbon emissions at each stage, T statei Indicates that logistics equipment isi The duration of each job in the job status, P i Represents the output power of logistics equipment, EF poweri represents the power emission factor, Fi Indicates fuel consumption, EF fueli represents the fuel emission factor, α(Ei,Li) Indicates the dynamic adjustment coefficient. α(Ei,Li) The calculation formula is:

[0115] ΔT=T−T ref , indicating the current temperature T With reference temperature T ref The difference between ΔH=H−H ref , indicating the current humidity H With reference humidity H ref The difference between W Indicates the current wind speed. ΔL=L−L ref , indicating the current load L The difference between the reference load and k1, k2, k3, k4 Indicates the weight of the dynamic adjustment coefficient.

[0116] Optionally, the generation unit can also be used to: based on time modeling, capture the dynamic conversion time points of logistics equipment between loading and unloading state, idling state and transportation state, and the operation duration of each operation state; based on space modeling, combine positioning data and area division algorithm to capture the dynamic path of logistics equipment in different spatial locations; based on operation state modeling, use deep learning model and positioning data to combine and analyze the state switching and load change of logistics equipment; generate the carbon emission footprint of the whole process using the following formula:

[0117] in, CF total represents the carbon emissions of the entire process, CF i (t) Indicates i Logistics equipment at a time t The instantaneous carbon emissions T Represents the total time of the logistics process.

[0118] Optionally, the generation unit may also be used to: verify the dynamic path, operation status and load change of the quasi-logistics equipment in combination with the image data and the positioning data, and output a complete carbon footprint report.

[0119] According to another aspect of the embodiments of the present application, a server or terminal for implementing the above-mentioned method for generating the dynamic carbon footprint of port cargo circulation is also provided.

[0120] Figure 4 is a structural block diagram of a terminal according to an embodiment of the present application, such as Figure 4 As shown, the terminal may include: one or more (only one is shown in the figure) processors 401, a memory 403, and a transmission device 405, such as Figure 4 As shown, the terminal may also include an input and output device 407.

[0121] Among them, the memory 403 can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for generating the dynamic carbon footprint of port cargo circulation in the embodiment of the present application. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 403, that is, realizing the above-mentioned method for generating the dynamic carbon footprint of port cargo circulation. The memory 403 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 403 may further include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0122] The above-mentioned transmission device 405 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 405 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 405 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0123] Specifically, the memory 403 is used to store application programs.

[0124] The processor 401 may call the application stored in the memory 403 through the transmission device 405 to perform the following steps: Collect image data, positioning data and environmental variables generated by port cargo during circulation, and perform time and space alignment on the image data, positioning data and environmental variables to form a multi-modal fused dynamic data set; Using artificial intelligence to detect activity level information of logistics equipment from the dynamic data set, wherein the activity level information includes equipment type, operation status, operation duration, and load change of the logistics equipment; The carbon emissions of port cargo in different logistics links are calculated by combining the dynamic adjustment coefficient and the activity level information through a multi-factor dynamic emission model, wherein the dynamic adjustment coefficient is used to correct power emissions and fuel emissions; Image data and positioning data are combined to build a dynamic correlation model of time, space and logistics equipment, and then the carbon emissions of port cargo in different logistics links are used to generate a dynamic carbon footprint of the entire process of port cargo in the circulation process.

[0125] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0126] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 It does not limit the structure of the above electronic device. For example, the terminal may also include Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 4 Different configurations are shown.

[0127] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0128] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute the program code of the method for generating a dynamic carbon footprint of port cargo circulation.

[0129] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0130] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Collect image data, positioning data and environmental variables generated by port cargo during circulation, and perform time and space alignment on the image data, positioning data and environmental variables to form a multi-modal fused dynamic data set; Using artificial intelligence to detect activity level information of logistics equipment from the dynamic data set, wherein the activity level information includes equipment type, operation status, operation duration, and load change of the logistics equipment; The carbon emissions of port cargo in different logistics links are calculated by combining the dynamic adjustment coefficient and the activity level information through a multi-factor dynamic emission model, wherein the dynamic adjustment coefficient is used to correct power emissions and fuel emissions; Image data and positioning data are combined to build a dynamic correlation model of time, space and logistics equipment, and then the carbon emissions of port cargo in different logistics links are used to generate a dynamic carbon footprint of the entire process of port cargo in the circulation process.

[0131] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0132] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0133] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0134] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0135] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0136] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0139] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for generating dynamic carbon footprint of port cargo circulation, characterized in that: include: Collect image data, positioning data and environmental variables generated by port cargo during circulation, and perform time and space alignment on the image data, positioning data and environmental variables to form a multi-modal fused dynamic data set; Using artificial intelligence to detect activity level information of logistics equipment from the dynamic data set, wherein the activity level information includes equipment type, operation status, operation duration, and load change of the logistics equipment; The carbon emissions of port cargo in different logistics links are calculated by combining the dynamic adjustment coefficient and the activity level information through a multi-factor dynamic emission model, wherein the dynamic adjustment coefficient is used to correct power emissions and fuel emissions; The image data and positioning data are combined to build a dynamic correlation model of time, space and logistics equipment, and then the carbon emissions of port cargo in different logistics links are used to generate a dynamic carbon footprint of the entire process of port cargo in the circulation process.

2. The method according to claim 1, characterized in that The image data, positioning data and environmental variables generated by the port cargo during the circulation process are collected, and the image data, positioning data and environmental variables are aligned in time and space to form a multi-modal fused dynamic data set, including: The image data of logistics equipment is collected by fixed cameras and drones, the running track, running speed and location information of the logistics equipment are obtained by the positioning module on the logistics equipment, and the temperature, humidity and wind speed of the port operating environment are collected by temperature and humidity sensors and anemometers. The positioning data includes the running track, the running speed and the location information, and the environmental variables include temperature, humidity and wind speed; Based on the timestamp synchronization technology and the space alignment technology, the image data, the positioning data and the environmental variables are aligned in time and space to form a multi-modal fused dynamic data set.

3. The method according to claim 1, characterized in that Artificial intelligence is used to detect the activity level information of logistics equipment from the dynamic data set, including: Using a deep learning model to perform target detection on the image data to identify equipment categories, operating states, and load changes; Use the time series model LSTM to track and predict the dynamic changes of job status; The operating time of the logistics equipment in the operating state is calculated through the image data, and the dynamic load of the logistics equipment is estimated in combination with the load change. L current =L base +ΔL ,in, L base is the load before the change, ΔL is the load variation; The operation status and the operation duration are verified in combination with the positioning data.

4. The method according to claim 3, characterized in that The operation status includes loading and unloading status, idling status and transportation status. The operation status is verified in combination with the positioning data, including: When the running speed determined according to the positioning data is greater than 0, it is verified that the logistics equipment is in a transport state; When the running speed determined according to the positioning data is equal to 0, it is verified that the logistics equipment is in a loading and unloading state or an idling state.

5. The method according to claim 1, characterized in that The carbon emissions of port cargo in different logistics links are calculated through a multi-factor dynamic emission model, combined with the dynamic adjustment coefficient and the activity level information, including: Based on the multi-factor dynamic emission model, calculate the carbon emissions of logistics equipment under different operating conditions CF : in, CF Indicates the carbon emissions at each stage, T statei Indicates that logistics equipment is i The duration of each job in the job status, P i Represents the output power of logistics equipment, EF poweri represents the power emission factor, Fi Indicates fuel consumption, EF fueli represents the fuel emission factor, α(Ei,Li) Indicates the dynamic adjustment coefficient. α(Ei,Li) The calculation formula is: ΔT=T−T ref , indicating the current temperature T With reference temperature T ref The difference between ΔH=H−H ref , indicating the current humidity H With reference humidity H ref The difference between W Indicates the current wind speed. ΔL=L−L ref , indicating the current load L The difference between the reference load and k1, k2, k3, k4 Indicates the weight of the dynamic adjustment coefficient.

6. The method according to claim 1, characterized in that Combine image data and positioning data to build a dynamic correlation model of time, space and logistics equipment, and then use the carbon emissions of port cargo in different logistics links to generate the dynamic carbon footprint of the entire process of port cargo in the circulation process, including: Based on time modeling, capture the dynamic transition time points of logistics equipment between loading and unloading state, idling state and transportation state, as well as the operation duration of each operation state; Based on spatial modeling, combined with positioning data and regional division algorithms, the dynamic paths of logistics equipment in different spatial locations are captured; Based on operation status modeling, the deep learning model and positioning data are combined to analyze the state switching and load changes of logistics equipment; The full process carbon footprint is generated using the following formula: in, CF total represents the carbon emissions of the entire process, CF i (t) Indicates i Logistics equipment at a time t The instantaneous carbon emissions, T Represents the total time of the logistics process.

7. The method according to claim 6, characterized in that In the process of combining the image data and the positioning data to construct a dynamic correlation model of time, space and logistics equipment, and then using the carbon emissions of port cargo in different logistics links to generate a full-process dynamic carbon footprint of the port cargo in the circulation process, the method also includes: The image data and the positioning data are combined to verify the dynamic path, operation status and load change of the quasi-logistics equipment, and output a complete carbon footprint report.

8. A device for generating dynamic carbon footprint of port cargo circulation, characterized in that: include: A collection unit, used to collect image data, positioning data and environmental variables generated by port cargo during circulation, and to perform time and space alignment on the image data, the positioning data and the environmental variables to form a multi-modal fused dynamic data set; a detection unit, configured to detect activity level information of logistics equipment from the dynamic data set using artificial intelligence, wherein the activity level information includes equipment type, operation status, operation duration, and load change of the logistics equipment; A calculation unit, used to calculate the carbon emissions of port cargo in different logistics links through a multi-factor dynamic emission model, combined with a dynamic adjustment coefficient and the activity level information, wherein the dynamic adjustment coefficient is used to correct power emissions and fuel emissions; The generation unit is used to combine image data and positioning data to build a dynamic correlation model of time, space and logistics equipment, and then use the carbon emissions of port goods in different logistics links to generate a dynamic carbon footprint of the entire process of port goods in the circulation process.

9. A computer-readable storage medium, characterized in that: The storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the method described in any one of claims 1 to 7 through the computer program.

Images