Intelligent forklift management system and method based on AI driving behavior analysis

Abstract

The application provides a smart forklift management system and method based on AI driving behavior analysis, which comprises the following steps: establishing a three-dimensional model of a forklift and a digital twin model of the forklift according to the three-dimensional model; generating a basic cargo loading and unloading model according to the digital twin model; generating a basic driver operation model by combining the basic cargo loading and unloading model and the digital twin model; obtaining current driver data, current driving behavior data, current working environment data and current cargo data; generating a first loading and unloading model according to the current working environment data, the current cargo data and the basic cargo loading and unloading model; generating a first operation model by combining the first loading and unloading model, the current driver data and the basic driver operation model; generating an operation adjustment scheme according to the current driving behavior data and the first operation model; and adjusting the working parameters of the forklift according to the operation adjustment scheme. The application can realize intelligent management of forklift operation by comprehensively utilizing various data sources and models, and improve the working efficiency and safety.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a smart forklift management system and method based on AI driving behavior analysis. Background Technology

[0002] In recent years, with the rapid advancement of mobile robot technology, its application in logistics warehousing, industrial production, and other fields has become increasingly widespread. Forklifts, with their unique multi-level cargo handling capabilities, have become indispensable key equipment in these scenarios. However, in practical applications, forklift operations face numerous challenges: limited storage space, complex cargo handling environments, and confined operating spaces. To ensure operational safety and avoid collisions, cargo handling failures, positioning deviations, and other issues, forklift systems must possess high-precision operational control capabilities. However, existing forklift management solutions suffer from low levels of intelligence, low control precision, and low management efficiency. Summary of the Invention

[0003] Based on the above-mentioned problems, this invention proposes an intelligent forklift management system and method based on AI driving behavior analysis. By comprehensively utilizing multiple data sources and models, it can achieve intelligent management of forklift operation, thereby improving work efficiency and safety.

[0004] In view of this, one aspect of the present invention proposes a smart forklift management method based on AI driving behavior analysis, comprising:

[0005] Acquire forklift 3D data, forklift attribute data, forklift historical work data, forklift historical work environment data, forklift driver data, and forklift driver historical operation data;

[0006] A three-dimensional model of the forklift is established based on the forklift's three-dimensional data and attribute data.

[0007] A digital twin model of the forklift is established by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data.

[0008] A basic model for loading and unloading goods is generated based on the forklift digital twin model;

[0009] A basic driver operation model is generated based on the basic cargo loading and unloading model and the forklift digital twin model.

[0010] Acquire the forklift's current driver data, current driving behavior data, current working environment data, and current cargo data;

[0011] A first loading and unloading model for the current cargo is generated based on the current working environment data, the current cargo data, and the basic cargo loading and unloading model.

[0012] The first operation model of the current driver is generated based on the first loading and unloading model, the current driver data, and the driver's basic operation model.

[0013] An operation adjustment plan is generated based on the current driving behavior data and the first operation model;

[0014] Adjust the forklift's operating parameters according to the aforementioned operation adjustment plan.

[0015] Optionally, the step of establishing a digital twin model of the forklift by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data includes:

[0016] The process of establishing a physical feature model of a forklift based on the three-dimensional model of the forklift includes: extracting structural parameter data from the three-dimensional model of the forklift to establish a basic structural model of the forklift; mapping the power system parameters, braking system parameters, and steering system parameters from the forklift attribute data to the basic structural model of the forklift to generate a physical feature model of the forklift.

[0017] The process of establishing a forklift dynamic behavior model based on the forklift's historical working data includes: performing time-series analysis on the forklift's historical working data to extract motion characteristic data of the forklift under different working conditions; using machine learning algorithms to train the motion characteristic data to establish a forklift dynamic behavior prediction model; and associating and mapping the forklift dynamic behavior prediction model with the forklift physical characteristic model to form a forklift dynamic behavior model.

[0018] An environmental interaction model is established based on the historical working environment data of the forklift, including: analyzing the historical working environment data of the forklift, identifying environmental characteristics and their influencing factors on the operation of the forklift; establishing a correlation model between environmental characteristics and dynamic behavior of the forklift; and integrating the correlation model with the dynamic behavior model of the forklift to obtain an environmental interaction model.

[0019] The driver operation model is established based on the forklift driver data and the forklift driver's historical operation data, including: extracting features from the forklift driver's historical operation data to identify the driver's operation mode; combining the forklift driver data to establish a personalized driver operation feature model; and associating the personalized driver operation feature model with the environmental interaction model to obtain the driver operation model.

[0020] Integrating the above models, a forklift digital twin model is established, including: constructing a multi-dimensional data association matrix to realize data interaction between sub-models; establishing a unified data update mechanism to ensure the real-time performance of the model; and generating the forklift digital twin model.

[0021] Optionally, the step of generating a basic cargo loading and unloading model based on the forklift digital twin model includes:

[0022] Constructing a forklift pallet-retrieving sub-model includes: extracting fork motion parameters and power parameters from the forklift digital twin model; analyzing historical successful pallet-retrieving case data based on machine learning algorithms to extract optimal pallet-retrieving trajectory features; constructing a fork motion trajectory prediction model based on the fork motion parameters, power parameters, and optimal pallet-retrieving trajectory features; and establishing an adaptive alignment mechanism between the fork and pallet positions based on the fork motion trajectory prediction model and environmental perception data to obtain the forklift pallet-retrieving sub-model.

[0023] Establishing a pallet balance detection sub-model includes: extracting fork load-bearing data and pressure distribution data from the forklift digital twin model; establishing a pallet stress analysis model based on the fork load-bearing data and pressure distribution data to calculate the stress state of the pallet at different positions; constructing a pallet stability evaluation index system based on the pallet stress analysis model; and designing a real-time pallet balance state monitoring algorithm based on the pallet stress analysis model and the pallet stability evaluation index system to obtain the pallet balance detection sub-model.

[0024] The process of generating a center of gravity change prediction model includes: extracting forklift load status data from the forklift digital twin model; analyzing the influence of different cargo types on the forklift center of gravity based on the forklift load status data and the forklift 3D model, and establishing a correlation model between cargo weight and forklift center of gravity position; and constructing a real-time prediction algorithm for the center of gravity of the forklift-cargo system to generate the center of gravity change prediction model.

[0025] Constructing a forklift driving sub-model includes: extracting forklift motion feature data from the forklift digital twin model; combining the forklift motion feature data and the center of gravity change prediction model to calculate the optimal driving parameters under different load conditions, establishing a speed-steering-load safety constraint model, and generating an adaptive driving path planning algorithm to obtain the forklift driving sub-model.

[0026] Establishing a pallet unloading sub-model includes: extracting fork descent control parameters from the forklift digital twin model, analyzing the spatial constraints of the target position, establishing a precise pallet placement trajectory model, constructing a dynamic adjustment mechanism for the unloading process, and obtaining the pallet unloading sub-model.

[0027] Integrate the various sub-models to generate a complete basic model for cargo loading and unloading, including: establishing data interaction interfaces between sub-models; designing a collaborative operation mechanism for sub-models; and constructing an overall model optimization and adjustment algorithm.

[0028] Optionally, the step of generating a basic driver operation model based on the basic cargo loading and unloading model and the forklift digital twin model includes:

[0029] Based on the basic cargo loading and unloading model, a standard operation sequence model is constructed, including: extracting key operation nodes of each sub-model from the basic cargo loading and unloading model; sequentially sorting the key operation nodes to form a basic operation chain; setting safety parameter thresholds and operation tolerance ranges for each operation node; and establishing logical associations and dependencies between operation nodes.

[0030] The environmental adaptation model is constructed based on the forklift digital twin model, including: extracting environmental feature parameters from the forklift digital twin model; analyzing the degree of influence of different environmental features on operation based on the environmental feature parameters; establishing a mapping relationship between environmental features and operation parameters; and constructing an environmental adaptive adjustment mechanism for operation parameters.

[0031] Constructing a driver competence assessment model includes: extracting operational features from historical driving data; establishing a driver skill level assessment system; constructing a driver operating habit model; and generating personalized driver operating preference features.

[0032] Establish a cargo feature recognition model, including: analyzing the loading and unloading characteristics of different cargo types; establishing a correlation model between cargo attributes and operational requirements; constructing a real-time cargo status monitoring mechanism; and generating cargo-related operational constraints.

[0033] Generate operational paradigm templates, including: adjusting standard operating sequences by combining environmental adaptation models; setting personalized operating parameters based on driver competence assessment results; incorporating cargo characteristic constraints to form specific operating guidelines; and establishing a dynamic optimization mechanism for operational paradigms.

[0034] The basic operation model for drivers is constructed, including: integrating operation paradigm templates and establishing a multi-scenario operation rule library; designing a real-time adjustment algorithm for the operation model; constructing an operation feedback evaluation mechanism; and realizing the self-optimization function of the operation model.

[0035] Optionally, the step of generating a first loading and unloading model for the current cargo based on the current working environment data, the current cargo data, and the cargo loading and unloading basic model includes:

[0036] Analyze current work environment data to generate environmental constraints, including: identifying spatial limitation parameters of the current work area; extracting environmental feature data such as ground conditions and lighting conditions; detecting the distribution of surrounding obstacles; and generating a set of environmental constraint parameters.

[0037] Analyze current cargo data and extract cargo characteristic parameters, including: obtaining basic parameters such as cargo weight, size, and shape; identifying the cargo's center of gravity and stress characteristics; determining cargo loading and unloading requirements and precautions; and generating a set of cargo characteristic parameters.

[0038] Selecting suitable sub-models from the basic cargo loading and unloading model includes: matching the corresponding forklift pallet picking sub-model based on cargo characteristic parameters; selecting an appropriate pallet balance detection sub-model based on cargo weight; configuring a center of gravity change prediction model in combination with cargo characteristics; and selecting appropriate forklift driving sub-model and pallet unloading sub-model based on environmental constraints.

[0039] The selected sub-models are optimized by: adjusting the operating parameters of each sub-model according to environmental constraints; correcting the threshold settings of the model based on cargo characteristics; optimizing the collaborative configuration between sub-models; and generating an optimized model parameter set.

[0040] Construct the first loading and unloading model for the current cargo, including: integrating and optimizing the various sub-models; establishing a data interaction mechanism between models; setting real-time adjustment strategies for the models; and generating a complete loading and unloading model.

[0041] Optionally, the step of generating the first operating model of the current driver based on the first loading / unloading model, the current driver data, and the driver's basic operating model includes:

[0042] Analyze current driver data to establish personalized characteristic models, including: extracting drivers' historical operation data and behavioral characteristics; analyzing drivers' skill levels and areas of expertise; identifying drivers' operating habits and preferences; and establishing indicators for evaluating drivers' current status.

[0043] Model matching based on the driver's basic operation model includes: selecting an operation paradigm that matches the current driver's characteristics from the driver's basic operation model; adjusting the operation parameter thresholds according to the driver's skill level; modifying the operation sequence based on the driver's operating habits; and generating a preliminary personalized operation plan.

[0044] Operational optimization is performed in conjunction with the first loading and unloading model, including: comparing the personalized operation plan with the requirements of the first loading and unloading model; identifying potential operational risks and difficulties; adjusting operation parameters according to loading and unloading requirements; and establishing an operational safety protection mechanism.

[0045] Constructing a real-time adaptive mechanism includes: designing dynamic adjustment algorithms for operating parameters; establishing an operating feedback evaluation system; developing emergency response plans; and generating operational correction strategies.

[0046] Generate the current driver's primary operating model, including: integrating and optimizing the operating plan; establishing a real-time monitoring and feedback mechanism; setting personalized operating prompts and warnings; and forming a complete operating guidance model.

[0047] Optionally, the step of generating an operation adjustment scheme based on the current driving behavior data and the first operation model includes:

[0048] Real-time analysis of current driving behavior data, including: collecting real-time operating parameters of the driver, including steering angle, acceleration, and braking force; extracting current driving state features, including speed control, path selection, and fork operation; identifying abnormal driving behavior points, including sharp turns, sudden braking, and fork sway; and generating a current driving behavior feature set.

[0049] The difference analysis with the first operation model includes: comparing the current driving behavior characteristics with the first operation model in real time; calculating the deviation values ​​of each operation parameter; assessing the impact of the deviation on operational safety and efficiency; and generating a deviation characteristic report.

[0050] Risk assessment based on deviation characteristics includes: quantifying the safety risks of deviation characteristics; predicting the potential consequences of deviation behavior; identifying operational items that need to be prioritized for adjustment; and generating a risk level assessment report.

[0051] Develop targeted adjustment strategies, including: designing adjustment priorities based on risk levels; generating specific improvement suggestions for each item to be adjusted; designing gradual adjustment steps; and establishing evaluation criteria for adjustment effectiveness.

[0052] Generate an operational adjustment plan, including: integrating adjustment strategies to form a complete adjustment plan; designing the timing of plan execution; establishing a feedback mechanism for plan execution; and constructing a dynamic optimization mechanism for the plan.

[0053] Optionally, the step of adjusting the forklift's operating parameters according to the operation adjustment scheme includes:

[0054] The analysis of the operation adjustment plan and determination of the parameter adjustment range include: extracting specific parameter adjustment items from the operation adjustment plan; obtaining the target adjustment value and adjustment tolerance range of each parameter; determining the priority order of parameter adjustment; and establishing the correlation and constraint relationships between parameters.

[0055] Perform safety pre-inspections, including: assessing the impact of parameter adjustments on forklift stability; verifying whether the adjusted parameters are within the safety threshold range; analyzing potential risks during the parameter adjustment process; and generating a safety assessment report.

[0056] Develop a parameter adjustment execution strategy, including: designing adjustment steps based on the safety assessment results; developing a gradual adjustment curve for each parameter; establishing a buffer mechanism for parameter adjustment; and setting emergency termination conditions for the adjustment process.

[0057] The parameters to be adjusted include: gradually adjusting the power system parameters, including maximum speed and acceleration; optimizing the steering system parameters, including steering sensitivity and maximum turning angle; adjusting the hydraulic system parameters, including fork lifting speed and tilt angle; and updating the braking system parameters, including braking force and response time.

[0058] Establish a real-time monitoring and feedback mechanism, including: real-time monitoring of the effect of parameter adjustments; collection of driver operation feedback; detection of equipment operating status; and generation of adjustment effect evaluation reports.

[0059] Optionally, the step of extracting key operation nodes of each sub-model from the basic cargo loading and unloading model includes:

[0060] The key operational nodes of the fork pallet retrieval sub-model are analyzed, including: extracting key parameter points in the fork leveling stage, including initial height and horizontal angle; identifying control points in the fork insertion stage, including insertion speed, depth, and angle; extracting state points in the fork lifting stage, including lifting speed and target height; and establishing a node sequence model of the pallet retrieval process.

[0061] Key nodes of the pallet balance detection sub-model are extracted, including: identifying weight distribution detection points, including left and right balance points and front and back balance points; extracting key pressure sensing points, including pressure values ​​at each support point; determining stability judgment nodes, including tilt angle and sway amplitude; and generating a node state matrix for balance detection.

[0062] The key nodes of the center of gravity change prediction model are analyzed, including: identifying static center of gravity measurement points, including unloaded center of gravity and fully loaded center of gravity; extracting dynamic center of gravity change points, including center of gravity offset during acceleration and turning; determining critical state points, including the maximum allowable offset; and establishing a monitoring node network for center of gravity changes.

[0063] Extract key nodes from the forklift driving sub-model, including: identifying speed control nodes, including start, cruise, and deceleration points; extracting steering control points, including steering start, maximum turning angle, and return-to-center point; determining path planning points, including obstacle avoidance points and turning points; and generating a control node chain for the driving process.

[0064] The key nodes of the pallet unloading sub-model are analyzed, including: identifying positioning and alignment points, including horizontal position and vertical height; extracting descent control points, including descent speed change points and buffer points; determining release judgment points, including pallet contact points and separation points; and establishing a node sequence table for the unloading process.

[0065] Another aspect of the present invention provides an intelligent forklift management system based on AI driving behavior analysis, for executing an intelligent forklift management method based on AI driving behavior analysis, comprising: a cloud server and an IoT server;

[0066] The cloud server is configured as follows:

[0067] Acquire forklift 3D data, forklift attribute data, forklift historical work data, forklift historical work environment data, forklift driver data, and forklift driver historical operation data;

[0068] A three-dimensional model of the forklift is established based on the forklift's three-dimensional data and attribute data.

[0069] A digital twin model of the forklift is established by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data.

[0070] A basic model for loading and unloading goods is generated based on the forklift digital twin model;

[0071] A basic driver operation model is generated based on the basic cargo loading and unloading model and the forklift digital twin model.

[0072] The IoT server is configured as follows:

[0073] Acquire the forklift's current driver data, current driving behavior data, current working environment data, and current cargo data;

[0074] A first loading and unloading model for the current cargo is generated based on the current working environment data, the current cargo data, and the basic cargo loading and unloading model.

[0075] The first operation model of the current driver is generated based on the first loading and unloading model, the current driver data, and the driver's basic operation model.

[0076] An operation adjustment plan is generated based on the current driving behavior data and the first operation model;

[0077] Adjust the forklift's operating parameters according to the aforementioned operation adjustment plan.

[0078] The present invention provides a smart forklift management method based on AI driving behavior analysis, comprising: acquiring forklift 3D data, forklift attribute data, forklift historical work data, forklift historical work environment data, forklift driver data, and forklift driver historical operation data; establishing a forklift 3D model based on the forklift 3D data and the forklift attribute data; establishing a forklift digital twin model based on the forklift 3D model, the forklift historical work data, the forklift historical work environment data, the forklift driver data, and the forklift driver historical operation data; and generating a basic model for loading and unloading goods based on the forklift digital twin model. The system implements a comprehensive modeling approach for forklifts, encompassing physical characteristics, dynamic behavior, environmental interaction, and driver operations. This involves: generating a basic driver operation model based on the cargo loading / unloading basic model and the forklift digital twin model; acquiring current driver data, current driving behavior data, current working environment data, and current cargo data; generating a first loading / unloading model for the current cargo based on the current working environment data, the current cargo data, and the cargo loading / unloading basic model; generating a first operation model for the current driver based on the first loading / unloading model, the current driver data, and the driver's basic operation model; generating an operation adjustment plan based on the current driving behavior data and the first operation model; and adjusting the forklift's operating parameters according to the operation adjustment plan. This approach achieves comprehensive modeling of the forklift's physical characteristics, dynamic behavior, environmental interaction, and driver operations. Clear relationships are established between the sub-models to ensure data consistency and integrity. It enables personalized modeling based on the operational characteristics of different drivers, adapting to operational needs in different working environments. Machine learning algorithms accurately predict the dynamic behavior of the forklift, predicting the impact of environmental changes on forklift operations. A unified data update mechanism ensures the model reflects the forklift's working status in real time, supporting real-time operation optimization and adjustment. The model architecture supports the integration of new data sources and features, facilitating subsequent functional expansion and optimization. This constitutes an intelligent, dynamic, and reliable digital twin system for forklifts, improving the timeliness, intelligence, safety, and accuracy of forklift management. Attached Figure Description

[0079] Figure 1 This is a flowchart of an embodiment of the intelligent forklift management method based on AI driving behavior analysis provided by the present invention;

[0080] Figure 2 This is a schematic block diagram of an intelligent forklift management system based on AI driving behavior analysis provided in one embodiment of the present invention. Detailed Implementation

[0081] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0082] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0083] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0084] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0085] The following reference Figures 1 to 2 This invention describes a smart forklift management system and method based on AI driving behavior analysis, provided by some embodiments of the present invention.

[0086] like Figure 1 As shown, one embodiment of the present invention provides a smart forklift management method based on AI driving behavior analysis, comprising:

[0087] Acquire forklift 3D data, forklift attribute data, forklift historical work data, forklift historical work environment data, forklift driver data, and forklift driver historical operation data;

[0088] Understandably, LiDAR (Light Detection and Ranging) devices can be used to perform multi-angle 3D scanning of the forklift to obtain high-precision 3D data; sensors (such as temperature and pressure sensors) can be installed on the forklift to monitor its performance parameters in real time; the forklift's technical specifications and attribute information can be obtained through APIs or databases provided by the forklift manufacturer; data loggers can be installed on the forklift to record historical data such as working time, load, and distance traveled; historical working data can be uploaded to a cloud platform for subsequent data analysis and querying; environmental monitoring sensors can be installed in the working environment to record environmental parameters such as temperature, humidity, and light; cameras can be installed to record the forklift's operation in different working environments to assist in analyzing the impact of the environment on the forklift's operation; biometric technologies (such as fingerprint and facial recognition) can be used to record the driver's identity information; driver training and certification records can be obtained through the enterprise's internal management system; monitoring devices can be installed on the forklift to record the driver's operating behaviors (such as acceleration, braking, and steering); and the driver's operating data can be uploaded to a data analysis platform for behavioral pattern analysis and historical data storage. Through these steps, various types of forklift data can be comprehensively acquired, providing a foundation for subsequent intelligent management and optimization.

[0089] A three-dimensional model of the forklift is established based on the forklift's three-dimensional data and attribute data.

[0090] In this step, select suitable 3D modeling software (such as SolidWorks, AutoCAD, CATIA, etc.). These software programs can handle complex geometric shapes and structural features and support importing data in various formats. Import the collected forklift 3D data into the selected modeling software. Based on the imported data, use modeling tools to create a 3D model of the forklift. This includes drawing the various components of the forklift (such as the frame, forks, wheels, etc.) and ensuring the accuracy of the dimensions and positional relationships between the components. Assign forklift attribute data (such as material type, weight, etc.) to the corresponding model components for subsequent analysis and simulation. While ensuring model accuracy, the model can be simplified to reduce computation and improve the efficiency of subsequent analysis. For example, ignore details that have little impact on structural strength, such as small holes and welds. If finite element analysis (FEA) is required later, the 3D model needs to be meshed and discretized into finite elements for mechanical analysis. Verify the accuracy of the 3D model by comparing it with an actual forklift. If discrepancies are found, the model needs to be adjusted. After the model is completed, functional testing can be performed to ensure that the model performs as expected under different working conditions. Through this step, a 3D model of the forklift can be successfully built based on the forklift's 3D and attribute data, providing a foundation for subsequent digital twin model construction and other analyses.

[0091] A digital twin model of the forklift is established by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data.

[0092] Based on the forklift digital twin model, a basic cargo loading and unloading model is generated (including a forklift pallet picking sub-model, a pallet balance detection sub-model, a center of gravity change prediction model, a forklift driving sub-model, a pallet unloading sub-model, etc.).

[0093] Based on the basic cargo loading and unloading model and the forklift digital twin model, a basic driver operation model is generated (which can be combined with different working environments, different drivers, different cargo, etc. to generate a basic driver operation paradigm).

[0094] Acquire the forklift's current driver data (including historical driving behavior data, historical vehicle type data, historical working environment data, historical transported goods data, etc.), current driving behavior data, current working environment data, and current goods data;

[0095] Understandably, by installing various sensors on the forklift, including GPS, accelerometers, gyroscopes, and load sensors, the operating status of the forklift and the driver's operational behavior can be monitored in real time; on-board terminal equipment can be configured to record and store driver operation data, working environment data, and cargo information; a data recording system can be established to store the real-time collected data in a local or cloud database. This system should support the query and management of historical data; the database structure should be designed to ensure effective storage and retrieval of historical driving behavior data, historical driven vehicle data, historical working environment data, and historical transported cargo data; real-time driver data, including current driving behavior data, current working environment data, and current cargo data, should be acquired through the on-board terminal and sensors; historical data related to the current driver, including historical driving behavior, historical driven vehicle model, historical working environment, and historical transported cargo data, should be obtained through the database query interface; and real-time data should be integrated with historical data to form a complete driver data profile. This can be achieved through data analytics tools, which help identify driver operating patterns and behavioral characteristics; by using data analytics techniques (such as machine learning algorithms) to analyze the integrated data, driver behavioral trends and potential problems can be identified; visualization tools can be used to display the analysis results in the form of charts or dashboards, making it easy for managers and drivers to understand and use; based on the analysis results, real-time feedback can be provided to drivers to help them optimize their operating behavior and improve safety and efficiency. Through this step, current driver data and relevant historical data of the forklift can be effectively obtained, providing a foundation for intelligent management and optimization of forklifts.

[0096] A first loading and unloading model for the current cargo is generated based on the current working environment data, the current cargo data, and the basic cargo loading and unloading model.

[0097] The first operation model of the current driver is generated based on the first loading and unloading model, the current driver data, and the driver's basic operation model.

[0098] An operation adjustment plan is generated based on the current driving behavior data and the first operation model;

[0099] Adjust the forklift's operating parameters according to the aforementioned operation adjustment plan.

[0100] In this embodiment, by comprehensively utilizing multiple data sources and models, intelligent management of forklift operations can be achieved, improving work efficiency and safety. This AI-based management method has broad application prospects in modern logistics and warehousing management.

[0101] In some possible embodiments of the present invention, the step of establishing a digital twin model of the forklift by combining the forklift's three-dimensional model, the forklift's historical working data, the forklift's historical working environment data, the forklift driver's data, and the forklift driver's historical operation data includes:

[0102] Based on the aforementioned 3D model of the forklift, a physical feature model of the forklift is established, including:

[0103] Extract the structural parameter data from the three-dimensional model of the forklift and establish the basic structural model of the forklift.

[0104] The power system parameters, braking system parameters, and steering system parameters in the forklift attribute data are mapped to the forklift basic structure model to generate a forklift physical feature model.

[0105] A dynamic behavior model of the forklift is established based on the historical working data of the forklift, including:

[0106] Perform time-series analysis on the historical working data of the forklift to extract motion characteristic data of the forklift under different working conditions;

[0107] A forklift dynamic behavior prediction model is established by training the motion feature data using machine learning algorithms.

[0108] The forklift dynamic behavior prediction model is associated and mapped with the forklift physical feature model to form a forklift dynamic behavior model;

[0109] An environmental interaction model is established based on the historical working environment data of the forklift, including:

[0110] Analyze the historical working environment data of the forklift to identify environmental characteristics and their influencing factors on forklift operation;

[0111] Establish a correlation model between environmental characteristics and forklift dynamic behavior;

[0112] The association model is integrated with the forklift dynamic behavior model to obtain the environment interaction model;

[0113] A driver operation model is established based on the forklift driver data and the forklift driver's historical operation data, including:

[0114] Feature extraction is performed on the historical operation data of the forklift driver to identify the driver's operation mode;

[0115] Based on the forklift driver data, a personalized operation feature model of the driver is established;

[0116] The driver's personalized operation feature model is associated with the environmental interaction model to obtain the driver operation model;

[0117] Integrating the above models, a digital twin model of the forklift is established, including:

[0118] Construct a multi-dimensional data association matrix to enable data interaction between various sub-models;

[0119] Establish a unified data update mechanism to ensure the real-time performance of the model;

[0120] Generate a digital twin model of the forklift.

[0121] This embodiment achieves comprehensive modeling of forklift physical characteristics, dynamic behavior, environmental interaction, and driver operation. Clear relationships are established between the sub-models to ensure data consistency and integrity. It enables personalized modeling based on the operational characteristics of different drivers, adapting to operational needs in various working environments. Machine learning algorithms achieve accurate prediction of forklift dynamic behavior, predicting the impact of environmental changes on forklift operation. A unified data update mechanism ensures the model reflects the forklift's working status in real time, supporting real-time operation optimization and adjustment. The model architecture supports the integration of new data sources and features, facilitating subsequent functional expansion and optimization. This constitutes an intelligent, dynamic, and reliable digital twin system for forklifts, improving the timeliness, intelligence, safety, and accuracy of forklift management.

[0122] In some possible embodiments of the present invention, the step of generating a basic cargo loading and unloading model based on the forklift digital twin model includes:

[0123] Construct a forklift pallet-picking sub-model, including:

[0124] Extract fork motion parameters and power parameters from the forklift digital twin model;

[0125] Based on machine learning algorithms, historical successful pallet retrieval case data is analyzed to extract the optimal pallet retrieval trajectory features;

[0126] Based on the fork action parameters, power parameters, and optimal pallet picking trajectory characteristics, a fork motion trajectory prediction model is constructed.

[0127] Based on the fork motion trajectory prediction model and combined with environmental perception data, an adaptive alignment mechanism between the fork and pallet positions is established to obtain the fork pallet picking sub-model.

[0128] Establish a tray balance detection sub-model, including:

[0129] Extract fork load-bearing data and pressure distribution data from the forklift digital twin model;

[0130] Based on the fork load-bearing data and pressure distribution data, a pallet stress analysis model is established to calculate the stress state of the pallet at different locations.

[0131] Based on the pallet stress analysis model, a pallet stability assessment index system is constructed;

[0132] Based on the pallet stress analysis model and pallet stability evaluation index system, a real-time pallet balance state monitoring algorithm is designed to obtain a pallet balance detection sub-model.

[0133] Generate a model for predicting changes in the center of gravity, including:

[0134] Extract forklift load status data from the forklift digital twin model;

[0135] Based on forklift load data and forklift 3D model, we analyze the influence of different cargo types on forklift center of gravity and establish a correlation model between cargo weight and forklift center of gravity position.

[0136] Develop a real-time center of gravity prediction algorithm for the forklift-cargo system and generate a center of gravity change prediction model.

[0137] Construct a forklift driving sub-model, including:

[0138] Extract forklift motion feature data from the forklift digital twin model;

[0139] By combining forklift motion characteristic data and center of gravity change prediction model, the optimal driving parameters under different load conditions are calculated, a speed-steering-load safety constraint model is established, and an adaptive driving path planning algorithm is generated to obtain the forklift driving sub-model.

[0140] Establishing a pallet unloading sub-model includes: extracting fork descent control parameters from the forklift digital twin model, analyzing the spatial constraints of the target position, establishing a precise pallet placement trajectory model, constructing a dynamic adjustment mechanism for the unloading process, and obtaining the pallet unloading sub-model.

[0141] Integrate the various sub-models to generate a complete basic model for cargo loading and unloading, including: establishing data interaction interfaces between sub-models; designing a collaborative operation mechanism for sub-models; and constructing an overall model optimization and adjustment algorithm.

[0142] The solution in this embodiment significantly reduces the risk of cargo tipping through accurate center of gravity prediction and balance detection; real-time monitoring and adjustment ensure the stability of the loading and unloading process; adaptive path planning reduces unnecessary movement, a precise alignment mechanism improves loading and unloading speed, and a collaborative optimization algorithm achieves the optimal loading and unloading strategy; multi-dimensional monitoring and early warning mechanisms improve operational reliability, and dynamic adjustment capabilities adapt to different working conditions; it enables intelligent decision-making in the loading and unloading process, and adaptive adjustment capabilities enhance the system's intelligence; the model architecture supports the loading and unloading needs of different types of cargo, possessing good scenario adaptability and scalability; enabling the system to achieve safe, efficient, and intelligent cargo loading and unloading operations, while also possessing strong adaptability and scalability.

[0143] In some possible embodiments of the present invention, the step of generating a basic driver operation model based on the basic cargo loading and unloading model and the forklift digital twin model includes:

[0144] Based on the aforementioned basic cargo loading and unloading model, a standard operation sequence model is constructed, including:

[0145] Extract the key operation nodes of each sub-model from the basic cargo loading and unloading model;

[0146] The key operation nodes are sequentially sorted to form a basic operation chain;

[0147] In this step, firstly, an operation node dependency matrix is ​​established, including: analyzing the pre- and post-dependencies between key operation nodes; identifying mandatory sequential constraints between nodes; determining node groups that can be executed in parallel; and generating a node dependency table. Secondly, a node timing weight model is constructed, including: assigning execution duration weights to each operation node; setting time interval requirements between nodes; calculating the buffer time for node switching; and establishing a timing weight matrix. Next, node grouping optimization is performed, including: grouping nodes according to functional relevance; identifying critical path nodes within each group; determining connecting nodes between groups; and generating an optimized node group structure. Then, a timing sorting algorithm is executed, including: performing topological sorting based on the dependency matrix; applying timing weights for sequence optimization; handling the timing arrangement of parallel nodes; and generating a preliminary timing sequence. Furthermore, a basic operation chain is established, including: integrating the sorted node sequence; adding transition operations between nodes; setting checkpoints for the operation chain; and forming a complete basic operation chain structure. Finally, the operation chain is verified and optimized, including: verifying the logical integrity of the operation chain; verifying the rationality of the timing arrangement; optimizing the execution efficiency of the operation chain; and generating the final basic operation chain model. This step's approach ensures the rationality of the operation sequence, maintains the integrity of the operation chain, optimizes the sorting of operation nodes, improves execution efficiency, guarantees the continuity of operations, reduces the risk of operation interruption, supports dynamic node adjustment to adapt to different job requirements, accurately controls node timing, and guarantees operation quality.

[0148] Set safety parameter thresholds and operational tolerance ranges for each operating node;

[0149] Establish logical connections and dependencies between operation nodes;

[0150] An environment adaptation model is constructed based on the forklift digital twin model, including:

[0151] Environmental feature parameters are extracted from the digital twin model of the forklift;

[0152] Based on environmental characteristic parameters, analyze the degree of influence of different environmental characteristics on operation;

[0153] In this step, firstly, an environmental characteristic parameter classification system is constructed, including: classifying environmental characteristic parameters according to physical attributes, such as ground conditions, lighting conditions, and spatial constraints; classifying environmental characteristic parameters according to time-varying characteristics, such as fixed parameters, periodically changing parameters, and randomly changing parameters; and classifying environmental characteristic parameters according to their scope of influence, such as global influence parameters and local influence parameters; and generating an environmental characteristic parameter classification matrix. Secondly, an environment-operation impact assessment model is established, including: constructing a model of the impact of ground conditions on forklift driving stability; constructing a model of the impact of lighting conditions on operational accuracy; constructing a model of the impact of spatial constraints on the operation path; and constructing a coupled impact model of multiple environmental factors. Thirdly... The first step involves conducting a quantitative analysis of the environmental impact of various environmental characteristics, including: setting baseline values ​​and ranges of variation for each environmental characteristic parameter; calculating the impact coefficients of environmental characteristic changes on operational parameters; analyzing critical values ​​and risk thresholds for environmental characteristic changes; and generating a quantitative report on the environmental impact of these characteristics. The fourth step involves establishing an environmental adaptability assessment system, including: establishing operational difficulty scoring standards for different environmental characteristics; designing response strategies for environmental changes; constructing environmental adaptability assessment indicators; and generating environmental adaptability assessment results. The fifth step involves constructing an environmental impact early warning mechanism, including: setting monitoring thresholds for environmental characteristic changes; establishing environmental risk level classification standards; formulating response strategies for different risk levels; and forming a complete early warning and response mechanism. This step-by-step approach comprehensively covers environmental impact factors, establishes a complete analysis system, accurately quantifies environmental impacts, provides reliable assessment results, predicts the impact of environmental changes, allows for advance planning of response strategies, enables rapid response to environmental changes, dynamically adjusts operational parameters, promptly identifies environmental risks, and ensures operational safety.

[0154] Establish a mapping relationship between environmental characteristics and operating parameters;

[0155] Construct an environment-adaptive adjustment mechanism for operating parameters;

[0156] Constructing a driver competence assessment model includes: extracting operational features from historical driving data; establishing a driver skill level assessment system; constructing a driver operating habit model; and generating personalized driver operating preference features.

[0157] Establish a cargo feature recognition model, including:

[0158] Analyze the loading and unloading characteristics of different cargo types;

[0159] Establish a correlation model between cargo attributes and operational requirements;

[0160] In this step, various attribute data related to the goods are collected, including information such as goods type, weight, volume, packaging method, and hazard. This data can be obtained through barcode scanning, RFID tags, or manual input. Operational requirements related to loading, unloading, transportation, and storage of the goods are also collected, including loading and unloading procedures, required equipment, operating steps, and safety precautions. The collected data is cleaned to remove duplicate and erroneous information, ensuring accuracy and consistency. Data from different sources is standardized to facilitate subsequent analysis and modeling; for example, standardizing the classification criteria for goods types and the description methods of operational requirements. The basic structure of the model is determined, including the relationship between goods attributes and operational requirements; for example, entities can be used. - An ER model is used to represent the relationship between cargo attributes and operational requirements. Based on collected data, association rules between cargo attributes and operational requirements are established. This can be achieved through data mining techniques (such as association rule learning) to identify which cargo attributes correspond to which operational requirements. The effectiveness of the model is verified through actual operational data to check whether the model can accurately reflect the relationship between cargo attributes and operational requirements. The model is optimized based on the verification results, adjusting the association rules and model structure to improve the accuracy and applicability of the model. The established association model is applied to actual operations to guide the loading, unloading, transportation, and storage processes of goods. Feedback data is collected in practical applications to evaluate the model's effectiveness and continuously improve the model based on feedback. Through this step, an effective association model between cargo attributes and operational requirements can be established, thereby improving the efficiency and security of logistics and warehousing management.

[0161] Establish a real-time cargo status monitoring mechanism;

[0162] Generate operational constraints related to the goods;

[0163] Understandably, based on the characteristics of the goods (such as flammability, fragility, etc.) and the operating environment, safe operating constraints are determined. For example, the storage and transportation of flammable materials require adherence to specific safety regulations. Based on the equipment used (such as forklifts) and the characteristics of the goods, operational limitations of the equipment are determined, such as forklift load limits and operating radius. Based on the transportation and storage requirements of the goods, time-related constraints are determined, such as shelf life and delivery time. A constraint model is designed to systematically organize the collected constraints, which can be represented using mathematical or logical models. Through data analysis, association rules between goods attributes and operational constraints are established to ensure that corresponding operational constraints can be automatically generated under specific conditions. The effectiveness of the generated operational constraints is verified through actual operational data to check whether they can be effectively executed in actual operations. Based on the verification results and actual operational feedback, the constraints are adjusted and optimized to improve operational safety and efficiency. Through this step, goods-related operational constraints can be effectively generated, thereby improving the safety and efficiency of logistics and warehousing management.

[0164] Generate an operational paradigm template, including:

[0165] Adjust the standard operating procedure sequence by incorporating an environmental adaptation model;

[0166] Personalized operating parameters are set based on driver competence assessment results;

[0167] Incorporate cargo characteristic constraints to form specific operational guidelines;

[0168] Establish a dynamic optimization mechanism for operational paradigms;

[0169] Construct a basic operating model for the driver, including:

[0170] Integrate operation paradigm templates and establish a multi-scenario operation rule library;

[0171] Design a real-time adjustment algorithm for the operational model;

[0172] Establish an operational feedback and evaluation mechanism;

[0173] Implement the self-optimization function of the operation model.

[0174] This embodiment generates customized operation guidance based on driver characteristics, adapting to different drivers' operating habits and skill levels; it responds to environmental changes in real time, providing environmentally adaptable operation suggestions; it establishes complete operational safety boundaries, monitoring and issuing early warnings for dangerous operations in real time; it optimizes operation processes, reducing unnecessary actions; it provides optimal operation suggestions; it continuously optimizes the operation model, accumulating and utilizing excellent operational experience; and it supports multiple work scenarios to adapt to different types of cargo needs. This solution enables the system to provide personalized, safe, and efficient operation guidance for different drivers, while possessing continuous optimization and scenario adaptability capabilities.

[0175] In some possible embodiments of the present invention, the step of generating a first loading and unloading model for the current cargo based on the current working environment data, the current cargo data, and the cargo loading and unloading basic model includes:

[0176] Analyze current work environment data to generate environmental constraints, including: identifying spatial limitation parameters of the current work area; extracting environmental feature data such as ground conditions and lighting conditions; detecting the distribution of surrounding obstacles; and generating a set of environmental constraint parameters.

[0177] Analyze current cargo data and extract cargo characteristic parameters, including: obtaining basic parameters such as cargo weight, size, and shape; identifying the cargo's center of gravity and stress characteristics; determining cargo loading and unloading requirements and precautions; and generating a set of cargo characteristic parameters.

[0178] Selecting suitable sub-models from the basic cargo loading and unloading model includes: matching the corresponding forklift pallet picking sub-model based on cargo characteristic parameters; selecting an appropriate pallet balance detection sub-model based on cargo weight; configuring a center of gravity change prediction model in combination with cargo characteristics; and selecting appropriate forklift driving sub-model and pallet unloading sub-model based on environmental constraints.

[0179] The selected sub-models are optimized by: adjusting the operating parameters of each sub-model according to environmental constraints; correcting the threshold settings of the model based on cargo characteristics; optimizing the collaborative configuration between sub-models; and generating an optimized model parameter set.

[0180] Construct the first loading and unloading model for the current cargo, including: integrating and optimizing the various sub-models; establishing a data interaction mechanism between models; setting real-time adjustment strategies for the models; and generating a complete loading and unloading model.

[0181] The solution in this embodiment can adjust loading and unloading strategies in real time according to the current environment and cargo characteristics, quickly responding to changes in the environment and cargo status; optimize loading and unloading parameters for specific cargo characteristics, improving the accuracy of loading and unloading operations; fully consider environmental constraints and cargo characteristics to prevent potential safety hazards; optimize the loading and unloading process, reduce unnecessary actions, and provide the optimal loading and unloading path; support the loading and unloading needs of different types of cargo, and adapt to various working environment conditions. This solution enables the system to generate the optimal loading and unloading plan according to the actual situation, ensuring the safety and efficiency of operations.

[0182] In some possible embodiments of the present invention, the step of generating the first operating model of the current driver based on the first loading / unloading model, the current driver data, and the driver's basic operating model includes:

[0183] Analyze current driver data to establish personalized characteristic models, including: extracting drivers' historical operation data and behavioral characteristics; analyzing drivers' skill levels and areas of expertise; identifying drivers' operating habits and preferences; and establishing indicators for evaluating drivers' current status.

[0184] Model matching based on the driver's basic operation model includes: selecting an operation paradigm that matches the current driver's characteristics from the driver's basic operation model; adjusting the operation parameter thresholds according to the driver's skill level; modifying the operation sequence based on the driver's operating habits; and generating a preliminary personalized operation plan.

[0185] Operational optimization is performed in conjunction with the first loading and unloading model, including: comparing the personalized operation plan with the requirements of the first loading and unloading model; identifying potential operational risks and difficulties; adjusting operation parameters according to loading and unloading requirements; and establishing an operational safety protection mechanism.

[0186] Constructing a real-time adaptive mechanism includes: designing dynamic adjustment algorithms for operating parameters; establishing an operating feedback evaluation system; developing emergency response plans; and generating operational correction strategies.

[0187] Generate the current driver's primary operating model, including: integrating and optimizing the operating plan; establishing a real-time monitoring and feedback mechanism; setting personalized operating prompts and warnings; and forming a complete operating guidance model.

[0188] This embodiment of the solution fully considers the individual characteristics of drivers, providing operational suggestions that conform to driving habits; identifies and prevents potential risks, establishing a multi-layered safety protection mechanism; optimizes individual operating procedures, reducing unnecessary operational actions; quickly adapts to changes in operating conditions, providing timely operational adjustment suggestions; and supports driver skill improvement, accumulating optimized operating experience. This solution enables the system to provide the most suitable operating guidance for the current driver, while ensuring the safety and efficiency of operation.

[0189] In some possible embodiments of the present invention, the step of generating an operation adjustment scheme based on the current driving behavior data and the first operation model includes:

[0190] Real-time analysis of current driving behavior data, including: collecting real-time operating parameters of the driver, including steering angle, acceleration, and braking force; extracting current driving state features, including speed control, path selection, and fork operation; identifying abnormal driving behavior points, including sharp turns, sudden braking, and fork sway; and generating a current driving behavior feature set.

[0191] The difference analysis with the first operation model includes: comparing the current driving behavior characteristics with the first operation model in real time; calculating the deviation values ​​of each operation parameter; assessing the impact of the deviation on operational safety and efficiency; and generating a deviation characteristic report.

[0192] Risk assessment based on deviation characteristics includes: quantifying the safety risks of deviation characteristics; predicting the potential consequences of deviation behavior; identifying operational items that need to be prioritized for adjustment; and generating a risk level assessment report.

[0193] Develop targeted adjustment strategies, including: designing adjustment priorities based on risk levels; generating specific improvement suggestions for each item to be adjusted; designing gradual adjustment steps; and establishing evaluation criteria for adjustment effectiveness.

[0194] Generate an operational adjustment plan, including: integrating adjustment strategies to form a complete adjustment plan; designing the timing of plan execution; establishing a feedback mechanism for plan execution; and constructing a dynamic optimization mechanism for the plan.

[0195] This embodiment of the solution can detect operational deviations in real time and quickly generate adjustment suggestions; accurately identify operational problems and provide targeted improvement solutions; promptly warn of potential risks and prevent dangerous operating behaviors; dynamically adjust according to actual conditions and support incremental improvement; provide specific and feasible improvement steps for easy driver understanding and execution; and continuously improve the solution through feedback to promote improved driving skills. This solution enables the system to effectively identify and improve problems in driving operations, ensuring continuous improvement in the safety and efficiency of forklift operation.

[0196] In some possible embodiments of the present invention, the step of adjusting the operating parameters of the forklift according to the operation adjustment scheme includes:

[0197] The analysis of the operation adjustment plan and determination of the parameter adjustment range include: extracting specific parameter adjustment items from the operation adjustment plan; obtaining the target adjustment value and adjustment tolerance range of each parameter; determining the priority order of parameter adjustment; and establishing the correlation and constraint relationships between parameters.

[0198] Perform safety pre-inspections, including: assessing the impact of parameter adjustments on forklift stability; verifying whether the adjusted parameters are within the safety threshold range; analyzing potential risks during the parameter adjustment process; and generating a safety assessment report.

[0199] Develop a parameter adjustment execution strategy, including: designing adjustment steps based on the safety assessment results; developing a gradual adjustment curve for each parameter; establishing a buffer mechanism for parameter adjustment; and setting emergency termination conditions for the adjustment process.

[0200] The parameters to be adjusted include: gradually adjusting the power system parameters, including maximum speed and acceleration; optimizing the steering system parameters, including steering sensitivity and maximum turning angle; adjusting the hydraulic system parameters, including fork lifting speed and tilt angle; and updating the braking system parameters, including braking force and response time.

[0201] Establish a real-time monitoring and feedback mechanism, including: real-time monitoring of the effect of parameter adjustments; collection of driver operation feedback; detection of equipment operating status; and generation of adjustment effect evaluation reports.

[0202] The solution in this embodiment ensures the safety of the parameter adjustment process, preventing equipment failures caused by parameter adjustments; it enables gradual parameter adjustments, avoiding sudden changes that could affect operation; it accurately achieves target parameter values, maintaining coordination between parameters; it quickly responds to abnormal situations, supporting dynamic parameter adjustments; it records the parameter adjustment process for easy problem analysis and optimization; and it automates parameter adjustments with intelligent error prevention and protection. This solution enables the system to safely, reliably, and efficiently adjust forklift operating parameters, improving overall operational performance.

[0203] In some possible embodiments of the present invention, the step of extracting the key operation nodes of each sub-model from the basic cargo loading and unloading model includes:

[0204] The key operational nodes of the fork pallet retrieval sub-model are analyzed, including: extracting key parameter points in the fork leveling stage, including initial height and horizontal angle; identifying control points in the fork insertion stage, including insertion speed, depth, and angle; extracting state points in the fork lifting stage, including lifting speed and target height; and establishing a node sequence model of the pallet retrieval process.

[0205] Key nodes of the pallet balance detection sub-model are extracted, including: identifying weight distribution detection points, including left and right balance points and front and back balance points; extracting key pressure sensing points, including pressure values ​​at each support point; determining stability judgment nodes, including tilt angle and sway amplitude; and generating a node state matrix for balance detection.

[0206] The key nodes of the center of gravity change prediction model are analyzed, including: identifying static center of gravity measurement points, including unloaded center of gravity and fully loaded center of gravity; extracting dynamic center of gravity change points, including center of gravity offset during acceleration and turning; determining critical state points, including the maximum allowable offset; and establishing a monitoring node network for center of gravity changes.

[0207] Extract key nodes from the forklift driving sub-model, including: identifying speed control nodes, including start, cruise, and deceleration points; extracting steering control points, including steering start, maximum turning angle, and return-to-center point; determining path planning points, including obstacle avoidance points and turning points; and generating a control node chain for the driving process.

[0208] The key nodes of the pallet unloading sub-model are analyzed, including: identifying positioning and alignment points, including horizontal position and vertical height; extracting descent control points, including descent speed change points and buffer points; determining release judgment points, including pallet contact points and separation points; and establishing a node sequence table for the unloading process.

[0209] The solution in this embodiment can accurately identify key control points in each stage and establish precise operational reference standards; it can fully cover the entire loading and unloading process and establish a systematic node network; it can clarify the logical relationships between nodes and ensure the continuity of operation; it can support node adjustments under different working conditions and has dynamic optimization capabilities; it can achieve precise process control and provide clear operational guidance; it can effectively identify risk control points and establish multiple safety guarantees; and it can provide an accurate and complete control node foundation for subsequent operation models, ensuring the accuracy and safety of loading and unloading operations.

[0210] Please see Figure 2 Another embodiment of the present invention provides an intelligent forklift management system based on AI driving behavior analysis, for executing an intelligent forklift management method based on AI driving behavior analysis, including: a cloud server and an IoT server;

[0211] The cloud server is configured as follows:

[0212] Acquire forklift 3D data, forklift attribute data, forklift historical work data, forklift historical work environment data, forklift driver data, and forklift driver historical operation data;

[0213] A three-dimensional model of the forklift is established based on the forklift's three-dimensional data and attribute data.

[0214] A digital twin model of the forklift is established by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data.

[0215] A basic model for loading and unloading goods is generated based on the forklift digital twin model;

[0216] A basic driver operation model is generated based on the basic cargo loading and unloading model and the forklift digital twin model.

[0217] The IoT server is configured as follows:

[0218] Acquire the forklift's current driver data, current driving behavior data, current working environment data, and current cargo data;

[0219] A first loading and unloading model for the current cargo is generated based on the current working environment data, the current cargo data, and the basic cargo loading and unloading model.

[0220] The first operation model of the current driver is generated based on the first loading and unloading model, the current driver data, and the driver's basic operation model.

[0221] An operation adjustment plan is generated based on the current driving behavior data and the first operation model;

[0222] Adjust the forklift's operating parameters according to the aforementioned operation adjustment plan.

[0223] It should be known that, Figure 2 The block diagram of the AI-based driving behavior analysis intelligent forklift management system shown is for illustrative purposes only, and the number of modules shown does not limit the scope of protection of this invention. The AI-based driving behavior analysis intelligent forklift management system provided in this embodiment can be used to execute various embodiments of the corresponding AI-based driving behavior analysis intelligent forklift management method. For specific implementation details, please refer to the descriptions of the respective method embodiments, which will not be repeated here.

[0224] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0225] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0226] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0227] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0228] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0229] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0230] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0231] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0232] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.

Claims

1. A smart forklift management method based on AI driving behavior analysis, characterized in that, include: Acquire forklift 3D data, forklift attribute data, forklift historical work data, forklift historical work environment data, forklift driver data, and forklift driver historical operation data; A three-dimensional model of the forklift is established based on the forklift's three-dimensional data and attribute data. A digital twin model of the forklift is established by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data. A basic model for loading and unloading goods is generated based on the forklift digital twin model; A basic driver operation model is generated based on the basic cargo loading and unloading model and the forklift digital twin model. Acquire the forklift's current driver data, current driving behavior data, current working environment data, and current cargo data; A first loading and unloading model for the current cargo is generated based on the current working environment data, the current cargo data, and the basic cargo loading and unloading model. The first operation model of the current driver is generated based on the first loading and unloading model, the current driver data, and the driver's basic operation model. An operation adjustment plan is generated based on the current driving behavior data and the first operation model; Adjust the forklift's operating parameters according to the aforementioned operation adjustment plan.

2. The intelligent forklift management method based on AI driving behavior analysis according to claim 1, characterized in that, The step of establishing a digital twin model of the forklift by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data includes: The process of establishing a physical feature model of a forklift based on the three-dimensional model of the forklift includes: extracting structural parameter data from the three-dimensional model of the forklift to establish a basic structural model of the forklift; mapping the power system parameters, braking system parameters, and steering system parameters from the forklift attribute data to the basic structural model of the forklift to generate a physical feature model of the forklift. The process of establishing a forklift dynamic behavior model based on the forklift's historical working data includes: performing time-series analysis on the forklift's historical working data to extract motion characteristic data of the forklift under different working conditions; using machine learning algorithms to train the motion characteristic data to establish a forklift dynamic behavior prediction model; and associating and mapping the forklift dynamic behavior prediction model with the forklift physical characteristic model to form a forklift dynamic behavior model. An environmental interaction model is established based on the historical working environment data of the forklift, including: analyzing the historical working environment data of the forklift, identifying environmental characteristics and their influencing factors on the operation of the forklift; establishing a correlation model between environmental characteristics and dynamic behavior of the forklift; and integrating the correlation model with the dynamic behavior model of the forklift to obtain an environmental interaction model. The driver operation model is established based on the forklift driver data and the forklift driver's historical operation data, including: extracting features from the forklift driver's historical operation data to identify the driver's operation mode; combining the forklift driver data to establish a personalized driver operation feature model; and associating the personalized driver operation feature model with the environmental interaction model to obtain the driver operation model. Integrating the above models, a forklift digital twin model is established, including: constructing a multi-dimensional data association matrix to realize data interaction between sub-models; establishing a unified data update mechanism to ensure the real-time performance of the model; and generating the forklift digital twin model.

3. The intelligent forklift management method based on AI driving behavior analysis according to claim 2, characterized in that, The step of generating a basic cargo loading and unloading model based on the forklift digital twin model includes: Constructing a forklift pallet-retrieving sub-model includes: extracting fork motion parameters and power parameters from the forklift digital twin model; analyzing historical successful pallet-retrieving case data based on machine learning algorithms to extract optimal pallet-retrieving trajectory features; constructing a fork motion trajectory prediction model based on the fork motion parameters, power parameters, and optimal pallet-retrieving trajectory features; and establishing an adaptive alignment mechanism between the fork and pallet positions based on the fork motion trajectory prediction model and environmental perception data to obtain the forklift pallet-retrieving sub-model. Establishing a pallet balance detection sub-model includes: extracting fork load-bearing data and pressure distribution data from the forklift digital twin model; establishing a pallet stress analysis model based on the fork load-bearing data and pressure distribution data to calculate the stress state of the pallet at different positions; constructing a pallet stability evaluation index system based on the pallet stress analysis model; and designing a real-time pallet balance state monitoring algorithm based on the pallet stress analysis model and the pallet stability evaluation index system to obtain the pallet balance detection sub-model. The process of generating a center of gravity change prediction model includes: extracting forklift load status data from the forklift digital twin model; analyzing the influence of different cargo types on the forklift center of gravity based on the forklift load status data and the forklift 3D model, and establishing a correlation model between cargo weight and forklift center of gravity position; and constructing a real-time prediction algorithm for the center of gravity of the forklift-cargo system to generate the center of gravity change prediction model. Constructing a forklift driving sub-model includes: extracting forklift motion feature data from the forklift digital twin model; combining the forklift motion feature data and the center of gravity change prediction model to calculate the optimal driving parameters under different load conditions, establishing a speed-steering-load safety constraint model, and generating an adaptive driving path planning algorithm to obtain the forklift driving sub-model. Establishing a pallet unloading sub-model includes: extracting fork descent control parameters from the forklift digital twin model, analyzing the spatial constraints of the target position, establishing a precise pallet placement trajectory model, constructing a dynamic adjustment mechanism for the unloading process, and obtaining the pallet unloading sub-model. Integrate the various sub-models to generate a complete basic model for cargo loading and unloading, including: establishing data interaction interfaces between sub-models; designing a collaborative operation mechanism for sub-models; and constructing an overall model optimization and adjustment algorithm.

4. The intelligent forklift management method based on AI driving behavior analysis according to claim 3, characterized in that, The step of generating a basic driver operation model based on the basic cargo loading and unloading model and the forklift digital twin model includes: Based on the basic cargo loading and unloading model, a standard operation sequence model is constructed, including: extracting key operation nodes of each sub-model from the basic cargo loading and unloading model; sequentially sorting the key operation nodes to form a basic operation chain; setting safety parameter thresholds and operation tolerance ranges for each operation node; and establishing logical associations and dependencies between operation nodes. The environmental adaptation model is constructed based on the forklift digital twin model, including: extracting environmental feature parameters from the forklift digital twin model; analyzing the degree of influence of different environmental features on operation based on the environmental feature parameters; establishing a mapping relationship between environmental features and operation parameters; and constructing an environmental adaptive adjustment mechanism for operation parameters. Constructing a driver competence assessment model includes: extracting operational features from historical driving data; establishing a driver skill level assessment system; constructing a driver operating habit model; and generating personalized driver operating preference features. Establish a cargo feature recognition model, including: analyzing the loading and unloading characteristics of different cargo types; establishing a correlation model between cargo attributes and operational requirements; constructing a real-time cargo status monitoring mechanism; and generating cargo-related operational constraints. Generate operational paradigm templates, including: adjusting standard operating sequences by combining environmental adaptation models; setting personalized operating parameters based on driver competence assessment results; incorporating cargo characteristic constraints to form specific operating guidelines; and establishing a dynamic optimization mechanism for operational paradigms. The basic operation model for drivers is constructed, including: integrating operation paradigm templates and establishing a multi-scenario operation rule library; designing a real-time adjustment algorithm for the operation model; constructing an operation feedback evaluation mechanism; and realizing the self-optimization function of the operation model.

5. The intelligent forklift management method based on AI driving behavior analysis according to claim 4, characterized in that, The step of generating the first loading and unloading model of the current cargo based on the current working environment data, the current cargo data, and the cargo loading and unloading basic model includes: Analyze current work environment data to generate environmental constraints, including: identifying spatial limitation parameters of the current work area; extracting environmental feature data such as ground conditions and lighting conditions; detecting the distribution of surrounding obstacles; and generating a set of environmental constraint parameters. Analyze current cargo data and extract cargo characteristic parameters, including: obtaining basic parameters such as cargo weight, size, and shape; identifying the cargo's center of gravity and stress characteristics; determining cargo loading and unloading requirements and precautions; and generating a set of cargo characteristic parameters. Selecting suitable sub-models from the basic cargo loading and unloading model includes: matching the corresponding forklift pallet picking sub-model based on cargo characteristic parameters; selecting an appropriate pallet balance detection sub-model based on cargo weight; configuring a center of gravity change prediction model in combination with cargo characteristics; and selecting appropriate forklift driving sub-model and pallet unloading sub-model based on environmental constraints. The selected sub-models are optimized by: adjusting the operating parameters of each sub-model according to environmental constraints; correcting the threshold settings of the model based on cargo characteristics; optimizing the collaborative configuration between sub-models; and generating an optimized model parameter set. Construct the first loading and unloading model for the current cargo, including: integrating and optimizing the various sub-models; establishing a data interaction mechanism between models; setting real-time adjustment strategies for the models; and generating a complete loading and unloading model.

6. The intelligent forklift management method based on AI driving behavior analysis according to claim 5, characterized in that, The step of generating the first operating model of the current driver based on the first loading / unloading model, the current driver data, and the driver's basic operating model includes: Analyze current driver data to establish personalized characteristic models, including: extracting drivers' historical operation data and behavioral characteristics; analyzing drivers' skill levels and areas of expertise; identifying drivers' operating habits and preferences; and establishing indicators for evaluating drivers' current status. Model matching based on the driver's basic operation model includes: selecting an operation paradigm that matches the current driver's characteristics from the driver's basic operation model; adjusting the operation parameter thresholds according to the driver's skill level; modifying the operation sequence based on the driver's operating habits; and generating a preliminary personalized operation plan. Operational optimization is performed in conjunction with the first loading and unloading model, including: comparing the personalized operation plan with the requirements of the first loading and unloading model; identifying potential operational risks and difficulties; adjusting operation parameters according to loading and unloading requirements; and establishing an operational safety protection mechanism. Constructing a real-time adaptive mechanism includes: designing dynamic adjustment algorithms for operating parameters; establishing an operational feedback evaluation system; developing emergency response plans; and generating operational correction strategies. Generate the current driver's primary operating model, including: integrating and optimizing the operating plan; establishing a real-time monitoring and feedback mechanism; setting personalized operating prompts and warnings; and forming a complete operating guidance model.

7. The intelligent forklift management method based on AI driving behavior analysis according to claim 6, characterized in that, The step of generating an operation adjustment plan based on the current driving behavior data and the first operation model includes: Real-time analysis of current driving behavior data, including: collecting real-time operating parameters of the driver, including steering angle, acceleration, and braking force; extracting current driving state features, including speed control, path selection, and fork operation; identifying abnormal driving behavior points, including sharp turns, sudden braking, and fork sway; and generating a current driving behavior feature set. The difference analysis with the first operation model includes: comparing the current driving behavior characteristics with the first operation model in real time; calculating the deviation values ​​of each operation parameter; assessing the impact of the deviation on operational safety and efficiency; and generating a deviation characteristic report. Risk assessment based on deviation characteristics includes: quantifying the safety risks of deviation characteristics; predicting the potential consequences of deviation behavior; identifying operational items that need to be prioritized for adjustment; and generating a risk level assessment report. Develop targeted adjustment strategies, including: designing adjustment priorities based on risk levels; generating specific improvement suggestions for each item to be adjusted; designing gradual adjustment steps; and establishing evaluation criteria for adjustment effectiveness. Generate an operational adjustment plan, including: integrating adjustment strategies to form a complete adjustment plan; designing the timing of plan execution; establishing a feedback mechanism for plan execution; and constructing a dynamic optimization mechanism for the plan.

8. The intelligent forklift management method based on AI driving behavior analysis according to claim 7, characterized in that, The step of adjusting the forklift's operating parameters according to the operation adjustment plan includes: The analysis of the operation adjustment plan and determination of the parameter adjustment range include: extracting specific parameter adjustment items from the operation adjustment plan; obtaining the target adjustment value and adjustment tolerance range of each parameter; determining the priority order of parameter adjustment; and establishing the correlation and constraint relationships between parameters. Perform safety pre-inspections, including: assessing the impact of parameter adjustments on forklift stability; verifying whether the adjusted parameters are within the safety threshold range; analyzing potential risks during the parameter adjustment process; and generating a safety assessment report. Develop a parameter adjustment execution strategy, including: designing adjustment steps based on the safety assessment results; developing a gradual adjustment curve for each parameter; establishing a buffer mechanism for parameter adjustment; and setting emergency termination conditions for the adjustment process. The parameters to be adjusted include: gradually adjusting the power system parameters, including maximum speed and acceleration; optimizing the steering system parameters, including steering sensitivity and maximum turning angle; adjusting the hydraulic system parameters, including fork lifting speed and tilt angle; and updating the braking system parameters, including braking force and response time. Establish a real-time monitoring and feedback mechanism, including: real-time monitoring of the effect of parameter adjustments; collection of driver operation feedback; detection of equipment operating status; and generation of adjustment effect evaluation reports.

9. The intelligent forklift management method based on AI driving behavior analysis according to claim 8, characterized in that, The steps for extracting key operation nodes of each sub-model from the basic cargo loading and unloading model include: The key operational nodes of the fork pallet retrieval sub-model are analyzed, including: extracting key parameter points in the fork leveling stage, including initial height and horizontal angle; identifying control points in the fork insertion stage, including insertion speed, depth, and angle; extracting state points in the fork lifting stage, including lifting speed and target height; and establishing a node sequence model of the pallet retrieval process. Key nodes of the pallet balance detection sub-model are extracted, including: identifying weight distribution detection points, including left and right balance points and front and back balance points; extracting key pressure sensing points, including pressure values ​​at each support point; determining stability judgment nodes, including tilt angle and sway amplitude; and generating a node state matrix for balance detection. The key nodes of the center of gravity change prediction model are analyzed, including: identifying static center of gravity measurement points, including unloaded center of gravity and fully loaded center of gravity; extracting dynamic center of gravity change points, including center of gravity offset during acceleration and turning; determining critical state points, including the maximum allowable offset; and establishing a monitoring node network for center of gravity changes. Extract key nodes from the forklift driving sub-model, including: identifying speed control nodes, including start, cruise, and deceleration points; extracting steering control points, including steering start, maximum turning angle, and return-to-center point; determining path planning points, including obstacle avoidance points and turning points; and generating a control node chain for the driving process. The key nodes of the pallet unloading sub-model are analyzed, including: identifying positioning and alignment points, including horizontal position and vertical height; extracting descent control points, including descent speed change points and buffer points; determining release judgment points, including pallet contact points and separation points; and establishing a node sequence table for the unloading process.

10. A smart forklift management system based on AI driving behavior analysis, used to execute the smart forklift management method based on AI driving behavior analysis as described in any one of claims 1 to 9, characterized in that, include: Cloud servers and IoT servers; The cloud server is configured as follows: Acquire forklift 3D data, forklift attribute data, forklift historical work data, forklift historical work environment data, forklift driver data, and forklift driver historical operation data; A three-dimensional model of the forklift is established based on the forklift's three-dimensional data and attribute data. A digital twin model of the forklift is established by combining the forklift's 3D model, historical working data, historical working environment data, driver data, and historical operation data. A basic model for loading and unloading goods is generated based on the forklift digital twin model; A basic driver operation model is generated based on the basic cargo loading and unloading model and the forklift digital twin model. The IoT server is configured as follows: Acquire the forklift's current driver data, current driving behavior data, current working environment data, and current cargo data; A first loading and unloading model for the current cargo is generated based on the current working environment data, the current cargo data, and the basic cargo loading and unloading model. The first operation model of the current driver is generated based on the first loading and unloading model, the current driver data, and the driver's basic operation model. An operation adjustment plan is generated based on the current driving behavior data and the first operation model; Adjust the forklift's operating parameters according to the aforementioned operation adjustment plan.

Images